{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning-1/papers/ran/14","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":14,"pages_in_order":15,"rows_per_page":100,"rows":[1301,1400],"of":1416,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning-1/papers/ran/1","prev":"/task/reinforcement-learning-1/papers/ran/13","next":"/task/reinforcement-learning-1/papers/ran/15","papers":[{"url":"/paper/multi-task-maximum-entropy-inverse","slug":"multi-task-maximum-entropy-inverse","title":"Multi-task Maximum Entropy Inverse Reinforcement Learning","date":"2018-05-22","arxiv_id":"1805.08882","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-task-maximum-entropy-inverse#ran","syntology_url":"https://syntology.ai/paper/1805.08882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.08882"}},"official":{"repos":["HumanCompatibleAI/population-irl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evolution-guided-policy-gradient-in","slug":"evolution-guided-policy-gradient-in","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.07917","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolution-guided-policy-gradient-in#ran","syntology_url":"https://syntology.ai/paper/1805.07917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07917"}},"official":{"repos":["ShawK91/erl_paper_nips18"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/where-do-you-think-youre-going-inferring","slug":"where-do-you-think-youre-going-inferring","title":"Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior","date":"2018-05-21","arxiv_id":"1805.08010","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/where-do-you-think-youre-going-inferring#ran","syntology_url":"https://syntology.ai/paper/1805.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.08010"}},"official":{"repos":["rddy/isql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/machine-teaching-for-inverse-reinforcement","slug":"machine-teaching-for-inverse-reinforcement","title":"Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications","date":"2018-05-20","arxiv_id":"1805.07687","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/machine-teaching-for-inverse-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1805.07687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07687"}},"official":{"repos":["dsbrown1331/machine-teaching-irl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-the-rubiks-cube-without-human","slug":"solving-the-rubiks-cube-without-human","title":"Solving the Rubik's Cube Without Human Knowledge","date":"2018-05-18","arxiv_id":"1805.07470","repositories_listed":9,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-the-rubiks-cube-without-human#ran","syntology_url":"https://syntology.ai/paper/1805.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07470"}},"official":null}},{"url":"/paper/end-to-end-reinforcement-learning-for","slug":"end-to-end-reinforcement-learning-for","title":"End-to-End Reinforcement Learning for Automatic Taxonomy Induction","date":"2018-05-10","arxiv_id":"1805.04044","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/end-to-end-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1805.04044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.04044"}},"official":{"repos":["morningmoni/TaxoRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/motion-planning-among-dynamic-decision-making","slug":"motion-planning-among-dynamic-decision-making","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01956","repositories_listed":6,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/motion-planning-among-dynamic-decision-making#ran","syntology_url":"https://syntology.ai/paper/1805.01956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01956"}},"official":{"repos":["mfe7/cadrl_ros"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reinforcement-learning-and-control-as","slug":"reinforcement-learning-and-control-as","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","date":"2018-05-02","arxiv_id":"1805.00909","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-and-control-as#ran","syntology_url":"https://syntology.ai/paper/1805.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.00909"}},"official":null}},{"url":"/paper/emergence-of-linguistic-communication-from","slug":"emergence-of-linguistic-communication-from","title":"Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input","date":"2018-04-11","arxiv_id":"1804.03984","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emergence-of-linguistic-communication-from#ran","syntology_url":"https://syntology.ai/paper/1804.03984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03984"}},"official":null}},{"url":"/paper/dora-the-explorer-directed-outreaching","slug":"dora-the-explorer-directed-outreaching","title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","date":"2018-04-11","arxiv_id":"1804.04012","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dora-the-explorer-directed-outreaching#ran","syntology_url":"https://syntology.ai/paper/1804.04012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04012"}},"official":{"repos":["borgr/DORA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-run-challenge-solutions-adapting","slug":"learning-to-run-challenge-solutions-adapting","title":"Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","date":"2018-04-02","arxiv_id":"1804.00361","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-run-challenge-solutions-adapting#ran","syntology_url":"https://syntology.ai/paper/1804.00361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00361"}},"official":{"repos":["AdamStelmaszczyk/learning2run"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/qmix-monotonic-value-function-factorisation","slug":"qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11485","repositories_listed":18,"syntology":{"n":11,"n_ran":9,"n_constructed":7,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qmix-monotonic-value-function-factorisation#ran","syntology_url":"https://syntology.ai/paper/1803.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11485"}},"official":{"repos":["oxwhirl/pymarl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-synergies-between-pushing-and","slug":"learning-synergies-between-pushing-and","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","date":"2018-03-27","arxiv_id":"1803.09956","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-synergies-between-pushing-and#ran","syntology_url":"https://syntology.ai/paper/1803.09956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09956"}},"official":{"repos":["andyzeng/visual-pushing-grasping"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/world-models","slug":"world-models","title":"World Models","date":"2018-03-27","arxiv_id":"1803.10122","repositories_listed":22,"syntology":{"n":38,"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":17,"n_honours":1,"n_violates":0,"n_no_contract":15,"n_pointer_only":3,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/world-models#ran","syntology_url":"https://syntology.ai/paper/1803.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10122"}},"official":null}},{"url":"/paper/simple-random-search-provides-a-competitive","slug":"simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","date":"2018-03-19","arxiv_id":"1803.07055","repositories_listed":26,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simple-random-search-provides-a-competitive#ran","syntology_url":"https://syntology.ai/paper/1803.07055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07055"}},"official":{"repos":["modestyachts/ARS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/variance-networks-when-expectation-does-not","slug":"variance-networks-when-expectation-does-not","title":"Variance Networks: When Expectation Does Not Meet Your Expectations","date":"2018-03-10","arxiv_id":"1803.03764","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/variance-networks-when-expectation-does-not#ran","syntology_url":"https://syntology.ai/paper/1803.03764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03764"}},"official":{"repos":["da-molchanov/variance-networks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerated-methods-for-deep-reinforcement","slug":"accelerated-methods-for-deep-reinforcement","title":"Accelerated Methods for Deep Reinforcement Learning","date":"2018-03-07","arxiv_id":"1803.02811","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/accelerated-methods-for-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1803.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02811"}},"official":null}},{"url":"/paper/distributed-prioritized-experience-replay","slug":"distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","repositories_listed":15,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/distributed-prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1803.00933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00933"}},"official":null}},{"url":"/paper/learning-by-playing-solving-sparse-reward","slug":"learning-by-playing-solving-sparse-reward","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","date":"2018-02-28","arxiv_id":"1802.10567","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-playing-solving-sparse-reward#ran","syntology_url":"https://syntology.ai/paper/1802.10567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10567"}},"official":{"repos":["hu-po/pySACQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-mirage-of-action-dependent-baselines-in","slug":"the-mirage-of-action-dependent-baselines-in","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","date":"2018-02-27","arxiv_id":"1802.10031","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-mirage-of-action-dependent-baselines-in#ran","syntology_url":"https://syntology.ai/paper/1802.10031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10031"}},"official":null}},{"url":"/paper/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","repositories_listed":67,"syntology":{"n":36,"n_ran":26,"n_constructed":0,"n_ran_checked":25,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":23,"n_pointer_only":21,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 1 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}},"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reinforcement-learning-on-web-interfaces","slug":"reinforcement-learning-on-web-interfaces","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","date":"2018-02-24","arxiv_id":"1802.08802","repositories_listed":5,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reinforcement-learning-on-web-interfaces#ran","syntology_url":"https://syntology.ai/paper/1802.08802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08802"}},"official":{"repos":["stanfordnlp/wge","worksheets.codalab.org/worksheets/0x0f25031bd42f4aabbc17625fe1484066"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/diversity-is-all-you-need-learning-skills","slug":"diversity-is-all-you-need-learning-skills","title":"Diversity is All You Need: Learning Skills without a Reward Function","date":"2018-02-16","arxiv_id":"1802.06070","repositories_listed":4,"syntology":{"n":11,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diversity-is-all-you-need-learning-skills#ran","syntology_url":"https://syntology.ai/paper/1802.06070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06070"}},"official":null}},{"url":"/paper/mean-field-multi-agent-reinforcement-learning","slug":"mean-field-multi-agent-reinforcement-learning","title":"Mean Field Multi-Agent Reinforcement Learning","date":"2018-02-15","arxiv_id":"1802.05438","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mean-field-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1802.05438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05438"}},"official":{"repos":["mlii/mfrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gep-pg-decoupling-exploration-and","slug":"gep-pg-decoupling-exploration-and","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","date":"2018-02-14","arxiv_id":"1802.05054","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gep-pg-decoupling-exploration-and#ran","syntology_url":"https://syntology.ai/paper/1802.05054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05054"}},"official":{"repos":["flowersteam/geppg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evolved-policy-gradients","slug":"evolved-policy-gradients","title":"Evolved Policy Gradients","date":"2018-02-13","arxiv_id":"1802.04821","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evolved-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/1802.04821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04821"}},"official":{"repos":["openai/EPG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reinforcement-learning-for-solving-the","slug":"reinforcement-learning-for-solving-the","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","date":"2018-02-12","arxiv_id":"1802.04240","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-for-solving-the#ran","syntology_url":"https://syntology.ai/paper/1802.04240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04240"}},"official":null}},{"url":"/paper/impala-scalable-distributed-deep-rl-with","slug":"impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","repositories_listed":24,"syntology":{"n":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/impala-scalable-distributed-deep-rl-with#ran","syntology_url":"https://syntology.ai/paper/1802.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01561"}},"official":{"repos":["deepmind/scalable_agent"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/safe-exploration-in-continuous-action-spaces","slug":"safe-exploration-in-continuous-action-spaces","title":"Safe Exploration in Continuous Action Spaces","date":"2018-01-26","arxiv_id":"1801.08757","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-exploration-in-continuous-action-spaces#ran","syntology_url":"https://syntology.ai/paper/1801.08757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.08757"}},"official":null}},{"url":"/paper/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","repositories_listed":86,"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/jointly-learning-to-construct-and-control","slug":"jointly-learning-to-construct-and-control","title":"Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning","date":"2018-01-04","arxiv_id":"1801.01432","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jointly-learning-to-construct-and-control#ran","syntology_url":"https://syntology.ai/paper/1801.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01432"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-for-unsupervised","slug":"deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","date":"2017-12-29","arxiv_id":"1801.00054","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/1801.00054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00054"}},"official":{"repos":["KaiyangZhou/vsumm-reinforce"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improving-exploration-in-evolution-strategies","slug":"improving-exploration-in-evolution-strategies","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","date":"2017-12-18","arxiv_id":"1712.06560","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-exploration-in-evolution-strategies#ran","syntology_url":"https://syntology.ai/paper/1712.06560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.06560"}},"official":{"repos":["uber-research/deep-neuroevolution"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/deep-neuroevolution-genetic-algorithms-are-a","slug":"deep-neuroevolution-genetic-algorithms-are-a","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","date":"2017-12-18","arxiv_id":"1712.06567","repositories_listed":12,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-neuroevolution-genetic-algorithms-are-a#ran","syntology_url":"https://syntology.ai/paper/1712.06567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.06567"}},"official":null}},{"url":"/paper/ai2-thor-an-interactive-3d-environment-for","slug":"ai2-thor-an-interactive-3d-environment-for","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","date":"2017-12-14","arxiv_id":"1712.05474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai2-thor-an-interactive-3d-environment-for#ran","syntology_url":"https://syntology.ai/paper/1712.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05474"}},"official":{"repos":["allenai/ai2thor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-low-cost-ethics-shaping-approach-for","slug":"a-low-cost-ethics-shaping-approach-for","title":"A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents","date":"2017-12-12","arxiv_id":"1712.04172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-low-cost-ethics-shaping-approach-for#ran","syntology_url":"https://syntology.ai/paper/1712.04172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.04172"}},"official":null}},{"url":"/paper/mastering-chess-and-shogi-by-self-play-with-a","slug":"mastering-chess-and-shogi-by-self-play-with-a","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","date":"2017-12-05","arxiv_id":"1712.01815","repositories_listed":62,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mastering-chess-and-shogi-by-self-play-with-a#ran","syntology_url":"https://syntology.ai/paper/1712.01815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.01815"}},"official":null}},{"url":"/paper/progressive-neural-architecture-search","slug":"progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","arxiv_id":"1712.00559","repositories_listed":18,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/progressive-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1712.00559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00559"}},"official":{"repos":["chenxi116/PNASNet.TF","tensorflow/models","chenxi116/PNASNet.pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-reinforcement-learning-for-sepsis","slug":"deep-reinforcement-learning-for-sepsis","title":"Deep Reinforcement Learning for Sepsis Treatment","date":"2017-11-27","arxiv_id":"1711.09602","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-for-sepsis#ran","syntology_url":"https://syntology.ai/paper/1711.09602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.09602"}},"official":{"repos":["darkefyre/sepsisrl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/ethical-challenges-in-data-driven-dialogue","slug":"ethical-challenges-in-data-driven-dialogue","title":"Ethical Challenges in Data-Driven Dialogue Systems","date":"2017-11-24","arxiv_id":"1711.09050","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ethical-challenges-in-data-driven-dialogue#ran","syntology_url":"https://syntology.ai/paper/1711.09050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.09050"}},"official":{"repos":["Breakend/EthicsInDialogue"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hindsight-policy-gradients","slug":"hindsight-policy-gradients","title":"Hindsight policy gradients","date":"2017-11-16","arxiv_id":"1711.06006","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hindsight-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/1711.06006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.06006"}},"official":null}},{"url":"/paper/sqlnet-generating-structured-queries-from","slug":"sqlnet-generating-structured-queries-from","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","date":"2017-11-13","arxiv_id":"1711.04436","repositories_listed":13,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/sqlnet-generating-structured-queries-from#ran","syntology_url":"https://syntology.ai/paper/1711.04436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04436"}},"official":null}},{"url":"/paper/treeqn-and-atreec-differentiable-tree","slug":"treeqn-and-atreec-differentiable-tree","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","date":"2017-10-31","arxiv_id":"1710.11417","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/treeqn-and-atreec-differentiable-tree#ran","syntology_url":"https://syntology.ai/paper/1710.11417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11417"}},"official":{"repos":["oxwhirl/treeqn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/regret-minimization-for-partially-observable","slug":"regret-minimization-for-partially-observable","title":"Regret Minimization for Partially Observable Deep Reinforcement Learning","date":"2017-10-31","arxiv_id":"1710.11424","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regret-minimization-for-partially-observable#ran","syntology_url":"https://syntology.ai/paper/1710.11424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11424"}},"official":null}},{"url":"/paper/backpropagation-through-the-void-optimizing","slug":"backpropagation-through-the-void-optimizing","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","date":"2017-10-31","arxiv_id":"1711.00123","repositories_listed":7,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":12,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/backpropagation-through-the-void-optimizing#ran","syntology_url":"https://syntology.ai/paper/1711.00123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00123"}},"official":{"repos":["duvenaud/relax"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visualizing-and-understanding-atari-agents","slug":"visualizing-and-understanding-atari-agents","title":"Visualizing and Understanding Atari Agents","date":"2017-10-31","arxiv_id":"1711.00138","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visualizing-and-understanding-atari-agents#ran","syntology_url":"https://syntology.ai/paper/1711.00138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00138"}},"official":{"repos":["greydanus/visualize_atari"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/eigenoption-discovery-through-the-deep","slug":"eigenoption-discovery-through-the-deep","title":"Eigenoption Discovery through the Deep Successor Representation","date":"2017-10-30","arxiv_id":"1710.11089","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eigenoption-discovery-through-the-deep#ran","syntology_url":"https://syntology.ai/paper/1710.11089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11089"}},"official":null}},{"url":"/paper/action-depedent-control-variates-for-policy","slug":"action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","date":"2017-10-30","arxiv_id":"1710.11198","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/action-depedent-control-variates-for-policy#ran","syntology_url":"https://syntology.ai/paper/1710.11198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11198"}},"official":null}},{"url":"/paper/learning-robust-rewards-with-adversarial","slug":"learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.11248","repositories_listed":7,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-robust-rewards-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/1710.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11248"}},"official":null}},{"url":"/paper/distributional-reinforcement-learning-with-1","slug":"distributional-reinforcement-learning-with-1","title":"Distributional Reinforcement Learning with Quantile Regression","date":"2017-10-27","arxiv_id":"1710.10044","repositories_listed":17,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distributional-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/1710.10044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10044"}},"official":null}},{"url":"/paper/flow-architecture-and-benchmarking-for","slug":"flow-architecture-and-benchmarking-for","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","date":"2017-10-16","arxiv_id":"1710.05465","repositories_listed":16,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-architecture-and-benchmarking-for#ran","syntology_url":"https://syntology.ai/paper/1710.05465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.05465"}},"official":{"repos":["cathywu/flow","flow-project/flow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rainbow-combining-improvements-in-deep","slug":"rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","arxiv_id":"1710.02298","repositories_listed":34,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rainbow-combining-improvements-in-deep#ran","syntology_url":"https://syntology.ai/paper/1710.02298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.02298"}},"official":null}},{"url":"/paper/detecting-adversarial-attacks-on-neural","slug":"detecting-adversarial-attacks-on-neural","title":"Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight","date":"2017-10-02","arxiv_id":"1710.00814","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/detecting-adversarial-attacks-on-neural#ran","syntology_url":"https://syntology.ai/paper/1710.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.00814"}},"official":{"repos":["yenchenlin/rl-attack-detection"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-deep-reinforcement-learning","slug":"self-supervised-deep-reinforcement-learning","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","date":"2017-09-29","arxiv_id":"1709.10489","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1709.10489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.10489"}},"official":{"repos":["gkahn13/gcg"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/overcoming-exploration-in-reinforcement","slug":"overcoming-exploration-in-reinforcement","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","date":"2017-09-28","arxiv_id":"1709.10089","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/overcoming-exploration-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1709.10089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.10089"}},"official":null}},{"url":"/paper/guided-deep-reinforcement-learning-for-swarm","slug":"guided-deep-reinforcement-learning-for-swarm","title":"Guided Deep Reinforcement Learning for Swarm Systems","date":"2017-09-18","arxiv_id":"1709.06011","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/guided-deep-reinforcement-learning-for-swarm#ran","syntology_url":"https://syntology.ai/paper/1709.06011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.06011"}},"official":null}},{"url":"/paper/scalable-trust-region-method-for-deep","slug":"scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-trust-region-method-for-deep#ran","syntology_url":"https://syntology.ai/paper/1708.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.05144"}},"official":{"repos":["openai/baselines"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/starcraft-ii-a-new-challenge-for","slug":"starcraft-ii-a-new-challenge-for","title":"StarCraft II: A New Challenge for Reinforcement Learning","date":"2017-08-16","arxiv_id":"1708.04782","repositories_listed":10,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/starcraft-ii-a-new-challenge-for#ran","syntology_url":"https://syntology.ai/paper/1708.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.04782"}},"official":{"repos":["deepmind/pysc2"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/neural-network-dynamics-for-model-based-deep","slug":"neural-network-dynamics-for-model-based-deep","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","date":"2017-08-08","arxiv_id":"1708.02596","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-network-dynamics-for-model-based-deep#ran","syntology_url":"https://syntology.ai/paper/1708.02596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02596"}},"official":null}},{"url":"/paper/imagination-augmented-agents-for-deep","slug":"imagination-augmented-agents-for-deep","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","date":"2017-07-19","arxiv_id":"1707.06203","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imagination-augmented-agents-for-deep#ran","syntology_url":"https://syntology.ai/paper/1707.06203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06203"}},"official":null}},{"url":"/paper/hindsight-experience-replay","slug":"hindsight-experience-replay","title":"Hindsight Experience Replay","date":"2017-07-05","arxiv_id":"1707.01495","repositories_listed":28,"syntology":{"n":16,"n_ran":16,"n_constructed":10,"n_ran_checked":11,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hindsight-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1707.01495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.01495"}},"official":null}},{"url":"/paper/efficient-probabilistic-performance-bounds","slug":"efficient-probabilistic-performance-bounds","title":"Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning","date":"2017-07-03","arxiv_id":"1707.00724","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-probabilistic-performance-bounds#ran","syntology_url":"https://syntology.ai/paper/1707.00724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.00724"}},"official":{"repos":["dsbrown1331/aaai-2018-code"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","repositories_listed":15,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-from-human","slug":"deep-reinforcement-learning-from-human","title":"Deep reinforcement learning from human preferences","date":"2017-06-12","arxiv_id":"1706.03741","repositories_listed":7,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-reinforcement-learning-from-human#ran","syntology_url":"https://syntology.ai/paper/1706.03741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03741"}},"official":null}},{"url":"/paper/multi-agent-actor-critic-for-mixed","slug":"multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","arxiv_id":"1706.02275","repositories_listed":86,"syntology":{"n":143,"n_ran":75,"n_constructed":54,"n_ran_checked":68,"n_instrument":7,"n_unverified":68,"n_honours":2,"n_violates":0,"n_no_contract":66,"n_pointer_only":99,"phrase":"75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified","sample_list":"/paper/multi-agent-actor-critic-for-mixed#ran","syntology_url":"https://syntology.ai/paper/1706.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02275"}},"official":{"repos":["openai/multiagent-particle-envs"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/parameter-space-noise-for-exploration","slug":"parameter-space-noise-for-exploration","title":"Parameter Space Noise for Exploration","date":"2017-06-06","arxiv_id":"1706.01905","repositories_listed":10,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parameter-space-noise-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.01905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.01905"}},"official":null}},{"url":"/paper/constrained-policy-optimization","slug":"constrained-policy-optimization","title":"Constrained Policy Optimization","date":"2017-05-30","arxiv_id":"1705.10528","repositories_listed":10,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/constrained-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1705.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10528"}},"official":null}},{"url":"/paper/concrete-dropout","slug":"concrete-dropout","title":"Concrete Dropout","date":"2017-05-22","arxiv_id":"1705.07832","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/concrete-dropout#ran","syntology_url":"https://syntology.ai/paper/1705.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07832"}},"official":null}},{"url":"/paper/learning-cooperative-visual-dialog-agents","slug":"learning-cooperative-visual-dialog-agents","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","date":"2017-03-20","arxiv_id":"1703.06585","repositories_listed":7,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-cooperative-visual-dialog-agents#ran","syntology_url":"https://syntology.ai/paper/1703.06585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06585"}},"official":null}},{"url":"/paper/evolution-strategies-as-a-scalable","slug":"evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","arxiv_id":"1703.03864","repositories_listed":23,"syntology":{"n":29,"n_ran":16,"n_constructed":0,"n_ran_checked":11,"n_instrument":5,"n_unverified":13,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/evolution-strategies-as-a-scalable#ran","syntology_url":"https://syntology.ai/paper/1703.03864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03864"}},"official":{"repos":["openai/evolution-strategies-starter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/model-agnostic-meta-learning-for-fast","slug":"model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","arxiv_id":"1703.03400","repositories_listed":85,"syntology":{"n":154,"n_ran":103,"n_constructed":35,"n_ran_checked":72,"n_instrument":31,"n_unverified":51,"n_honours":6,"n_violates":1,"n_no_contract":65,"n_pointer_only":57,"phrase":"103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified","sample_list":"/paper/model-agnostic-meta-learning-for-fast#ran","syntology_url":"https://syntology.ai/paper/1703.03400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03400"}},"official":{"repos":["cbfinn/maml","cbfinn/maml_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/robust-adversarial-reinforcement-learning","slug":"robust-adversarial-reinforcement-learning","title":"Robust Adversarial Reinforcement Learning","date":"2017-03-08","arxiv_id":"1703.02702","repositories_listed":7,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/robust-adversarial-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1703.02702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.02702"}},"official":null}},{"url":"/paper/neural-episodic-control","slug":"neural-episodic-control","title":"Neural Episodic Control","date":"2017-03-06","arxiv_id":"1703.01988","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-episodic-control#ran","syntology_url":"https://syntology.ai/paper/1703.01988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01988"}},"official":null}},{"url":"/paper/active-one-shot-learning","slug":"active-one-shot-learning","title":"Active One-shot Learning","date":"2017-02-21","arxiv_id":"1702.06559","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/active-one-shot-learning#ran","syntology_url":"https://syntology.ai/paper/1702.06559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.06559"}},"official":{"repos":["markpwoodward/active_osl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hybrid-code-networks-practical-and-efficient","slug":"hybrid-code-networks-practical-and-efficient","title":"Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning","date":"2017-02-10","arxiv_id":"1702.03274","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hybrid-code-networks-practical-and-efficient#ran","syntology_url":"https://syntology.ai/paper/1702.03274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.03274"}},"official":null}},{"url":"/paper/pathnet-evolution-channels-gradient-descent","slug":"pathnet-evolution-channels-gradient-descent","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","date":"2017-01-30","arxiv_id":"1701.08734","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pathnet-evolution-channels-gradient-descent#ran","syntology_url":"https://syntology.ai/paper/1701.08734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.08734"}},"official":null}},{"url":"/paper/adversarial-learning-for-neural-dialogue","slug":"adversarial-learning-for-neural-dialogue","title":"Adversarial Learning for Neural Dialogue Generation","date":"2017-01-23","arxiv_id":"1701.06547","repositories_listed":8,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-learning-for-neural-dialogue#ran","syntology_url":"https://syntology.ai/paper/1701.06547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06547"}},"official":null}},{"url":"/paper/cryptocurrency-portfolio-management-with-deep","slug":"cryptocurrency-portfolio-management-with-deep","title":"Cryptocurrency Portfolio Management with Deep Reinforcement Learning","date":"2016-12-05","arxiv_id":"1612.01277","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cryptocurrency-portfolio-management-with-deep#ran","syntology_url":"https://syntology.ai/paper/1612.01277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01277"}},"official":{"repos":["ZhengyaoJiang/PGPortfolio"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/self-critical-sequence-training-for-image","slug":"self-critical-sequence-training-for-image","title":"Self-critical Sequence Training for Image Captioning","date":"2016-12-02","arxiv_id":"1612.00563","repositories_listed":31,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-critical-sequence-training-for-image#ran","syntology_url":"https://syntology.ai/paper/1612.00563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00563"}},"official":null}},{"url":"/paper/neural-combinatorial-optimization-with","slug":"neural-combinatorial-optimization-with","title":"Neural Combinatorial Optimization with Reinforcement Learning","date":"2016-11-29","arxiv_id":"1611.09940","repositories_listed":10,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/neural-combinatorial-optimization-with#ran","syntology_url":"https://syntology.ai/paper/1611.09940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.09940"}},"official":null}},{"url":"/paper/learning-to-reinforcement-learn","slug":"learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","arxiv_id":"1611.05763","repositories_listed":9,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-to-reinforcement-learn#ran","syntology_url":"https://syntology.ai/paper/1611.05763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05763"}},"official":null}},{"url":"/paper/a-connection-between-generative-adversarial","slug":"a-connection-between-generative-adversarial","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","date":"2016-11-11","arxiv_id":"1611.03852","repositories_listed":3,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-connection-between-generative-adversarial#ran","syntology_url":"https://syntology.ai/paper/1611.03852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.03852"}},"official":null}},{"url":"/paper/rl2-fast-reinforcement-learning-via-slow","slug":"rl2-fast-reinforcement-learning-via-slow","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","date":"2016-11-09","arxiv_id":"1611.02779","repositories_listed":19,"syntology":{"n":21,"n_ran":11,"n_constructed":6,"n_ran_checked":8,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/rl2-fast-reinforcement-learning-via-slow#ran","syntology_url":"https://syntology.ai/paper/1611.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02779"}},"official":null}},{"url":"/paper/designing-neural-network-architectures-using","slug":"designing-neural-network-architectures-using","title":"Designing Neural Network Architectures using Reinforcement Learning","date":"2016-11-07","arxiv_id":"1611.02167","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-neural-network-architectures-using#ran","syntology_url":"https://syntology.ai/paper/1611.02167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02167"}},"official":null}},{"url":"/paper/modular-multitask-reinforcement-learning-with","slug":"modular-multitask-reinforcement-learning-with","title":"Modular Multitask Reinforcement Learning with Policy Sketches","date":"2016-11-06","arxiv_id":"1611.01796","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modular-multitask-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1611.01796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01796"}},"official":{"repos":["jacobandreas/psketch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/neural-architecture-search-with-reinforcement","slug":"neural-architecture-search-with-reinforcement","title":"Neural Architecture Search with Reinforcement Learning","date":"2016-11-05","arxiv_id":"1611.01578","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-architecture-search-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1611.01578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01578"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/input-convex-neural-networks","slug":"input-convex-neural-networks","title":"Input Convex Neural Networks","date":"2016-09-22","arxiv_id":"1609.07152","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/input-convex-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1609.07152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07152"}},"official":{"repos":["locuslab/icnn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seqgan-sequence-generative-adversarial-nets","slug":"seqgan-sequence-generative-adversarial-nets","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","date":"2016-09-18","arxiv_id":"1609.05473","repositories_listed":23,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":7,"n_honours":7,"n_violates":1,"n_no_contract":4,"n_pointer_only":13,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/seqgan-sequence-generative-adversarial-nets#ran","syntology_url":"https://syntology.ai/paper/1609.05473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.05473"}},"official":{"repos":["LantaoYu/SeqGAN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-option-critic-architecture","slug":"the-option-critic-architecture","title":"The Option-Critic Architecture","date":"2016-09-16","arxiv_id":"1609.05140","repositories_listed":10,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-option-critic-architecture#ran","syntology_url":"https://syntology.ai/paper/1609.05140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.05140"}},"official":null}},{"url":"/paper/progressive-neural-networks","slug":"progressive-neural-networks","title":"Progressive Neural Networks","date":"2016-06-15","arxiv_id":"1606.04671","repositories_listed":12,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/progressive-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1606.04671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04671"}},"official":null}},{"url":"/paper/generative-adversarial-imitation-learning","slug":"generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","arxiv_id":"1606.03476","repositories_listed":18,"syntology":{"n":36,"n_ran":24,"n_constructed":6,"n_ran_checked":22,"n_instrument":2,"n_unverified":12,"n_honours":2,"n_violates":1,"n_no_contract":19,"n_pointer_only":15,"phrase":"24 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/generative-adversarial-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1606.03476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03476"}},"official":null}},{"url":"/paper/deep-successor-reinforcement-learning","slug":"deep-successor-reinforcement-learning","title":"Deep Successor Reinforcement Learning","date":"2016-06-08","arxiv_id":"1606.02396","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-successor-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1606.02396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02396"}},"official":{"repos":["Ardavans/DSR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openai-gym","slug":"openai-gym","title":"OpenAI Gym","date":"2016-06-05","arxiv_id":"1606.01540","repositories_listed":45,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openai-gym#ran","syntology_url":"https://syntology.ai/paper/1606.01540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01540"}},"official":null}},{"url":"/paper/vime-variational-information-maximizing","slug":"vime-variational-information-maximizing","title":"VIME: Variational Information Maximizing Exploration","date":"2016-05-31","arxiv_id":"1605.09674","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vime-variational-information-maximizing#ran","syntology_url":"https://syntology.ai/paper/1605.09674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.09674"}},"official":null}},{"url":"/paper/vizdoom-a-doom-based-ai-research-platform-for","slug":"vizdoom-a-doom-based-ai-research-platform-for","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","date":"2016-05-06","arxiv_id":"1605.02097","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vizdoom-a-doom-based-ai-research-platform-for#ran","syntology_url":"https://syntology.ai/paper/1605.02097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02097"}},"official":{"repos":["mwydmuch/ViZDoom"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/continuous-deep-q-learning-with-model-based","slug":"continuous-deep-q-learning-with-model-based","title":"Continuous Deep Q-Learning with Model-based Acceleration","date":"2016-03-02","arxiv_id":"1603.00748","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continuous-deep-q-learning-with-model-based#ran","syntology_url":"https://syntology.ai/paper/1603.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.00748"}},"official":null}},{"url":"/paper/weight-normalization-a-simple","slug":"weight-normalization-a-simple","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","date":"2016-02-25","arxiv_id":"1602.07868","repositories_listed":9,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/weight-normalization-a-simple#ran","syntology_url":"https://syntology.ai/paper/1602.07868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.07868"}},"official":{"repos":["TimSalimans/weight_norm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-exploration-via-bootstrapped-dqn","slug":"deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","date":"2016-02-15","arxiv_id":"1602.04621","repositories_listed":6,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-exploration-via-bootstrapped-dqn#ran","syntology_url":"https://syntology.ai/paper/1602.04621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.04621"}},"official":null}},{"url":"/paper/value-iteration-networks","slug":"value-iteration-networks","title":"Value Iteration Networks","date":"2016-02-09","arxiv_id":"1602.02867","repositories_listed":8,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/value-iteration-networks#ran","syntology_url":"https://syntology.ai/paper/1602.02867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02867"}},"official":{"repos":["avivt/VIN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"b650f651e88b1f1167026446f961b4278fca1b30cf140576d88bafbe6e60d58f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}