{"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/policy-gradient-methods/papers/ran/1","list_of":"/task/policy-gradient-methods","task":"Policy Gradient Methods","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":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,33],"of":33,"counts":{"archive_papers_tagged":382,"with_a_code_link":103,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":382,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":32,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":32,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/policy-gradient-methods/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/reevaluating-policy-gradient-methods-for","slug":"reevaluating-policy-gradient-methods-for","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","date":"2025-02-13","arxiv_id":"2502.08938","repositories_listed":2,"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":3,"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/reevaluating-policy-gradient-methods-for#ran","syntology_url":"https://syntology.ai/paper/2502.08938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08938"}},"official":{"repos":["gabrfarina/exp-a-spiel","nathanlct/iig-rl-benchmark"],"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","unlocated"]}}},{"url":"/paper/fine-tuning-discrete-diffusion-models-with","slug":"fine-tuning-discrete-diffusion-models-with","title":"Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods","date":"2025-02-03","arxiv_id":"2502.01384","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/fine-tuning-discrete-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2502.01384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01384"}},"official":{"repos":["ozekri/SEPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bots-batch-bayesian-optimization-of-extended","slug":"bots-batch-bayesian-optimization-of-extended","title":"BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings","date":"2024-11-30","arxiv_id":"2412.00308","repositories_listed":0,"syntology":{"n":9,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/bots-batch-bayesian-optimization-of-extended#ran","syntology_url":"https://syntology.ai/paper/2412.00308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00308"}},"official":null}},{"url":"/paper/deep-policy-gradient-methods-without-batch","slug":"deep-policy-gradient-methods-without-batch","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","date":"2024-11-22","arxiv_id":"2411.15370","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/deep-policy-gradient-methods-without-batch#ran","syntology_url":"https://syntology.ai/paper/2411.15370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15370"}},"official":{"repos":["gauthamvasan/avg"],"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/steptool-a-step-grained-reinforcement","slug":"steptool-a-step-grained-reinforcement","title":"StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs","date":"2024-10-10","arxiv_id":"2410.07745","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/steptool-a-step-grained-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2410.07745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07745"}},"official":{"repos":["yuyq18/steptool"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-improvement-for-neural-combinatorial","slug":"self-improvement-for-neural-combinatorial","title":"Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement","date":"2024-03-22","arxiv_id":"2403.15180","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/self-improvement-for-neural-combinatorial#ran","syntology_url":"https://syntology.ai/paper/2403.15180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15180"}},"official":{"repos":["grimmlab/gumbeldore"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-diffusion-policies-for-offline-1","slug":"efficient-diffusion-policies-for-offline-1","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","date":"2023-05-31","arxiv_id":"2305.20081","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/efficient-diffusion-policies-for-offline-1#ran","syntology_url":"https://syntology.ai/paper/2305.20081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20081"}},"official":{"repos":["sail-sg/edp"],"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/continuous-mdp-homomorphisms-and-homomorphic","slug":"continuous-mdp-homomorphisms-and-homomorphic","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","date":"2022-09-15","arxiv_id":"2209.07364","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continuous-mdp-homomorphisms-and-homomorphic#ran","syntology_url":"https://syntology.ai/paper/2209.07364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07364"}},"official":{"repos":["sahandrez/homomorphic_policy_gradient"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/time-discretization-invariant-safe-action","slug":"time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","arxiv_id":"2111.03941","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/time-discretization-invariant-safe-action#ran","syntology_url":"https://syntology.ai/paper/2111.03941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03941"}},"official":{"repos":["artberryx/SAR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/global-optimality-and-finite-sample-analysis","slug":"global-optimality-and-finite-sample-analysis","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","date":"2021-11-04","arxiv_id":"2111.02997","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/global-optimality-and-finite-sample-analysis#ran","syntology_url":"https://syntology.ai/paper/2111.02997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02997"}},"official":{"repos":["ShangtongZhang/DeepRL"],"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/transform2act-learning-a-transform-and","slug":"transform2act-learning-a-transform-and","title":"Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design","date":"2021-10-07","arxiv_id":"2110.03659","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/transform2act-learning-a-transform-and#ran","syntology_url":"https://syntology.ai/paper/2110.03659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03659"}},"official":{"repos":["Khrylx/Transform2Act"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hindsight-value-function-for-variance","slug":"hindsight-value-function-for-variance","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","date":"2021-07-26","arxiv_id":"2107.12216","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 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) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hindsight-value-function-for-variance#ran","syntology_url":"https://syntology.ai/paper/2107.12216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12216"}},"official":null}},{"url":"/paper/experimental-design-for-mri-by-greedy-policy","slug":"experimental-design-for-mri-by-greedy-policy","title":"Experimental design for MRI by greedy policy search","date":"2020-10-30","arxiv_id":"2010.16262","repositories_listed":2,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":13,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 1 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/experimental-design-for-mri-by-greedy-policy#ran","syntology_url":"https://syntology.ai/paper/2010.16262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.16262"}},"official":{"repos":["Timsey/pg_mri"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pc-pg-policy-cover-directed-exploration-for","slug":"pc-pg-policy-cover-directed-exploration-for","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","date":"2020-07-16","arxiv_id":"2007.08459","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pc-pg-policy-cover-directed-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2007.08459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08459"}},"official":null}},{"url":"/paper/competitive-policy-optimization","slug":"competitive-policy-optimization","title":"Competitive Policy Optimization","date":"2020-06-18","arxiv_id":"2006.10611","repositories_listed":4,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/competitive-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2006.10611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10611"}},"official":{"repos":["manish-pra/copg"],"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/v-mpo-on-policy-maximum-a-posteriori-policy","slug":"v-mpo-on-policy-maximum-a-posteriori-policy","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","date":"2019-09-26","arxiv_id":"1909.12238","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/v-mpo-on-policy-maximum-a-posteriori-policy#ran","syntology_url":"https://syntology.ai/paper/1909.12238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12238"}},"official":null}},{"url":"/paper/rethink-global-reward-game-and-credit","slug":"rethink-global-reward-game-and-credit","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","date":"2019-07-11","arxiv_id":"1907.05707","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/rethink-global-reward-game-and-credit#ran","syntology_url":"https://syntology.ai/paper/1907.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05707"}},"official":{"repos":["hsvgbkhgbv/SQDDPG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ranking-policy-gradient","slug":"ranking-policy-gradient","title":"Ranking Policy Gradient","date":"2019-06-24","arxiv_id":"1906.09674","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/ranking-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/1906.09674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09674"}},"official":{"repos":["illidanlab/rpg"],"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/neural-logic-reinforcement-learning","slug":"neural-logic-reinforcement-learning","title":"Neural Logic Reinforcement Learning","date":"2019-04-24","arxiv_id":"1904.10729","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/neural-logic-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1904.10729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10729"}},"official":{"repos":["ZhengyaoJiang/NLRL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-action-spaces-for-reinforcement","slug":"rethinking-action-spaces-for-reinforcement","title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","date":"2019-02-23","arxiv_id":"1902.08858","repositories_listed":3,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/rethinking-action-spaces-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1902.08858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08858"}},"official":{"repos":["snakeztc/NeuralDialog-LaRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-expert-a-framework-for-using-action","slug":"actor-expert-a-framework-for-using-action","title":"Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement","date":"2018-10-22","arxiv_id":"1810.09103","repositories_listed":1,"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":0,"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/actor-expert-a-framework-for-using-action#ran","syntology_url":"https://syntology.ai/paper/1810.09103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09103"}},"official":{"repos":["samuelfneumann/greedyac"],"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/where-did-my-optimum-go-an-empirical-analysis","slug":"where-did-my-optimum-go-an-empirical-analysis","title":"Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods","date":"2018-10-05","arxiv_id":"1810.02525","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/where-did-my-optimum-go-an-empirical-analysis#ran","syntology_url":"https://syntology.ai/paper/1810.02525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02525"}},"official":{"repos":["facebookresearch/WhereDidMyOptimumGo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/remember-and-forget-for-experience-replay","slug":"remember-and-forget-for-experience-replay","title":"Remember and Forget for Experience Replay","date":"2018-07-16","arxiv_id":"1807.05827","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/remember-and-forget-for-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1807.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.05827"}},"official":{"repos":["cselab/smarties"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-learning-intrinsic-rewards-for-policy","slug":"on-learning-intrinsic-rewards-for-policy","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","date":"2018-04-17","arxiv_id":"1804.06459","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-learning-intrinsic-rewards-for-policy#ran","syntology_url":"https://syntology.ai/paper/1804.06459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.06459"}},"official":{"repos":["Hwhitetooth/lirpg"],"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/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/clipped-action-policy-gradient","slug":"clipped-action-policy-gradient","title":"Clipped Action Policy Gradient","date":"2018-02-21","arxiv_id":"1802.07564","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/clipped-action-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/1802.07564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07564"}},"official":{"repos":["pfnet-research/capg"],"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/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/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/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/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"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/high-dimensional-continuous-control-using","slug":"high-dimensional-continuous-control-using","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","date":"2015-06-08","arxiv_id":"1506.02438","repositories_listed":17,"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/high-dimensional-continuous-control-using#ran","syntology_url":"https://syntology.ai/paper/1506.02438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02438"}},"official":null}},{"url":"/paper/trust-region-policy-optimization","slug":"trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","arxiv_id":"1502.05477","repositories_listed":24,"syntology":{"n":17,"n_ran":7,"n_constructed":2,"n_ran_checked":6,"n_instrument":1,"n_unverified":10,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/trust-region-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1502.05477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.05477"}},"official":null}}],"record_sha256":"d4b85731a1a5a2df69ee3d519b68a5d13ff59f4dc9898751f901189a758479fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}