{"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-2/papers/37","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":37,"pages_in_order":135,"rows_per_page":100,"rows":[3601,3700],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2","prev":"/task/reinforcement-learning-2/papers/36","next":"/task/reinforcement-learning-2/papers/38","papers":[{"url":"/paper/paying-attention-to-function-words","slug":"paying-attention-to-function-words","title":"Paying Attention to Function Words","date":"2019-09-24","arxiv_id":"1909.11060","repositories_listed":1,"syntology":null},{"url":"/paper/loaded-dice-trading-off-bias-and-variance-in","slug":"loaded-dice-trading-off-bias-and-variance-in","title":"Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning","date":"2019-09-23","arxiv_id":"1909.10549","repositories_listed":1,"syntology":null},{"url":"/paper/190910008","slug":"190910008","title":"Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement Learning","date":"2019-09-22","arxiv_id":"1909.10008","repositories_listed":1,"syntology":null},{"url":"/paper/190909902","slug":"190909902","title":"Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture","date":"2019-09-21","arxiv_id":"1909.09902","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-optimization-for-iterative-learning","slug":"bayesian-optimization-for-iterative-learning","title":"Bayesian Optimization for Iterative Learning","date":"2019-09-20","arxiv_id":"1909.09593","repositories_listed":1,"syntology":null},{"url":"/paper/meta-inverse-reinforcement-learning-with","slug":"meta-inverse-reinforcement-learning-with","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","date":"2019-09-20","arxiv_id":"1909.09314","repositories_listed":1,"syntology":null},{"url":"/paper/modelicagym-applying-reinforcement-learning","slug":"modelicagym-applying-reinforcement-learning","title":"ModelicaGym: Applying Reinforcement Learning to Modelica Models","date":"2019-09-18","arxiv_id":"1909.08604","repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-policy-gradient-methods-with","slug":"sample-efficient-policy-gradient-methods-with","title":"Sample Efficient Policy Gradient Methods with Recursive Variance Reduction","date":"2019-09-18","arxiv_id":"1909.08610","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-for-open","slug":"hierarchical-reinforcement-learning-for-open","title":"Hierarchical Reinforcement Learning for Open-Domain Dialog","date":"2019-09-17","arxiv_id":"1909.07547","repositories_listed":1,"syntology":null},{"url":"/paper/mdp-playground-meta-features-in-reinforcement","slug":"mdp-playground-meta-features-in-reinforcement","title":"MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning","date":"2019-09-17","arxiv_id":"1909.07750","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/mdp-playground-meta-features-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1909.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07750"}},"official":{"repos":["automl/mdp-playground"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/control-synthesis-from-linear-temporal-logic","slug":"control-synthesis-from-linear-temporal-logic","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","date":"2019-09-16","arxiv_id":"1909.07299","repositories_listed":1,"syntology":null},{"url":"/paper/dl2-a-deep-learning-driven-scheduler-for-deep","slug":"dl2-a-deep-learning-driven-scheduler-for-deep","title":"DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters","date":"2019-09-13","arxiv_id":"1909.06040","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-portfolio","slug":"reinforcement-learning-for-portfolio","title":"Reinforcement Learning for Portfolio Management","date":"2019-09-12","arxiv_id":"1909.09571","repositories_listed":1,"syntology":null},{"url":"/paper/recsim-a-configurable-simulation-platform-for","slug":"recsim-a-configurable-simulation-platform-for","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","date":"2019-09-11","arxiv_id":"1909.04847","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/recsim-a-configurable-simulation-platform-for#ran","syntology_url":"https://syntology.ai/paper/1909.04847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04847"}},"official":{"repos":["google-research/recsim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-temporal-logic","slug":"reinforcement-learning-for-temporal-logic","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","date":"2019-09-11","arxiv_id":"1909.05304","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/reinforcement-learning-for-temporal-logic#ran","syntology_url":"https://syntology.ai/paper/1909.05304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05304"}},"official":{"repos":["grockious/lcrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-reproducibility-by-evaluating","slug":"a-survey-on-reproducibility-by-evaluating","title":"A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots","date":"2019-09-09","arxiv_id":"1909.03772","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":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) · 1 unverified","sample_list":"/paper/a-survey-on-reproducibility-by-evaluating#ran","syntology_url":"https://syntology.ai/paper/1909.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03772"}},"official":{"repos":["dti-research/SenseActExperiments"],"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/clickbait-sensational-headline-generation","slug":"clickbait-sensational-headline-generation","title":"Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning","date":"2019-09-09","arxiv_id":"1909.03582","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-anderson-acceleration-for-off","slug":"regularized-anderson-acceleration-for-off","title":"Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning","date":"2019-09-07","arxiv_id":"1909.03245","repositories_listed":1,"syntology":null},{"url":"/paper/drlviz-understanding-decisions-and-memory-in","slug":"drlviz-understanding-decisions-and-memory-in","title":"DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning","date":"2019-09-06","arxiv_id":"1909.02982","repositories_listed":1,"syntology":null},{"url":"/paper/rewarding-coreference-resolvers-for-being","slug":"rewarding-coreference-resolvers-for-being","title":"Rewarding Coreference Resolvers for Being Consistent with World Knowledge","date":"2019-09-05","arxiv_id":"1909.02392","repositories_listed":1,"syntology":null},{"url":"/paper/spatiotemporally-constrained-action-space","slug":"spatiotemporally-constrained-action-space","title":"Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents","date":"2019-09-05","arxiv_id":"1909.02583","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-comparison-on-imitation-learning","slug":"an-empirical-comparison-on-imitation-learning","title":"An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation","date":"2019-08-28","arxiv_id":"1908.10835","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/an-empirical-comparison-on-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1908.10835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.10835"}},"official":{"repos":["ddddwy/Reinforce-Paraphrase-Generation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/guided-dialog-policy-learning-reward","slug":"guided-dialog-policy-learning-reward","title":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","date":"2019-08-28","arxiv_id":"1908.10719","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-value-iteration-cvi-reinforcement","slug":"continuous-value-iteration-cvi-reinforcement","title":"Continuous Value Iteration (CVI) Reinforcement Learning and Imaginary Experience Replay (IER) for learning multi-goal, continuous action and state space controllers","date":"2019-08-27","arxiv_id":"1908.10255","repositories_listed":1,"syntology":null},{"url":"/paper/universal-policies-to-learn-them-all","slug":"universal-policies-to-learn-them-all","title":"Universal Policies to Learn Them All","date":"2019-08-24","arxiv_id":"1908.09184","repositories_listed":1,"syntology":null},{"url":"/paper/double-reinforcement-learning-for-efficient","slug":"double-reinforcement-learning-for-efficient","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","date":"2019-08-22","arxiv_id":"1908.08526","repositories_listed":1,"syntology":null},{"url":"/paper/opponent-aware-reinforcement-learning","slug":"opponent-aware-reinforcement-learning","title":"Opponent Aware Reinforcement Learning","date":"2019-08-22","arxiv_id":"1908.08773","repositories_listed":1,"syntology":null},{"url":"/paper/automated-quantum-programming-via","slug":"automated-quantum-programming-via","title":"Automated quantum programming via reinforcement learning for combinatorial optimization","date":"2019-08-21","arxiv_id":"1908.08054","repositories_listed":1,"syntology":null},{"url":"/paper/araml-a-stable-adversarial-training-framework","slug":"araml-a-stable-adversarial-training-framework","title":"ARAML: A Stable Adversarial Training Framework for Text Generation","date":"2019-08-20","arxiv_id":"1908.07195","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/araml-a-stable-adversarial-training-framework#ran","syntology_url":"https://syntology.ai/paper/1908.07195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07195"}},"official":{"repos":["kepei1106/ARAML"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/an-autonomous-performance-testing-framework","slug":"an-autonomous-performance-testing-framework","title":"An Autonomous Performance Testing Framework using Self-Adaptive Fuzzy Reinforcement Learning","date":"2019-08-19","arxiv_id":"1908.06900","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-in-world-earth","slug":"deep-reinforcement-learning-in-world-earth","title":"Deep reinforcement learning in World-Earth system models to discover sustainable management strategies","date":"2019-08-15","arxiv_id":"1908.05567","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/deep-reinforcement-learning-in-world-earth#ran","syntology_url":"https://syntology.ai/paper/1908.05567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05567"}},"official":{"repos":["fstrnad/pyDRLinWESM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-based-graph-to","slug":"reinforcement-learning-based-graph-to","title":"Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation","date":"2019-08-14","arxiv_id":"1908.04942","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/reinforcement-learning-based-graph-to#ran","syntology_url":"https://syntology.ai/paper/1908.04942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04942"}},"official":{"repos":["hugochan/RL-based-Graph2Seq-for-NQG"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-question-refinement-with-deep","slug":"generative-question-refinement-with-deep","title":"Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System","date":"2019-08-13","arxiv_id":"1908.05604","repositories_listed":1,"syntology":null},{"url":"/paper/is-deep-reinforcement-learning-really","slug":"is-deep-reinforcement-learning-really","title":"Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field","date":"2019-08-13","arxiv_id":"1908.04683","repositories_listed":1,"syntology":null},{"url":"/paper/a-review-on-deep-reinforcement-learning-for","slug":"a-review-on-deep-reinforcement-learning-for","title":"A review on Deep Reinforcement Learning for Fluid Mechanics","date":"2019-08-12","arxiv_id":"1908.04127","repositories_listed":1,"syntology":null},{"url":"/paper/vision-based-navigation-using-deep","slug":"vision-based-navigation-using-deep","title":"Vision-based Navigation Using Deep Reinforcement Learning","date":"2019-08-08","arxiv_id":"1908.03627","repositories_listed":1,"syntology":null},{"url":"/paper/free-lunch-saliency-via-attention-in-atari","slug":"free-lunch-saliency-via-attention-in-atari","title":"Free-Lunch Saliency via Attention in Atari Agents","date":"2019-08-07","arxiv_id":"1908.02511","repositories_listed":1,"syntology":null},{"url":"/paper/dueling-posterior-sampling-for-preference","slug":"dueling-posterior-sampling-for-preference","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","date":"2019-08-04","arxiv_id":"1908.01289","repositories_listed":1,"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/dueling-posterior-sampling-for-preference#ran","syntology_url":"https://syntology.ai/paper/1908.01289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01289"}},"official":{"repos":["ernovoseller/DuelingPosteriorSampling"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/health-informed-policy-gradients-for-multi","slug":"health-informed-policy-gradients-for-multi","title":"Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning","date":"2019-08-02","arxiv_id":"1908.01022","repositories_listed":1,"syntology":null},{"url":"/paper/control-of-nonlinear-complex-and-black-boxed","slug":"control-of-nonlinear-complex-and-black-boxed","title":"Control of nonlinear, complex and black-boxed greenhouse system with reinforcement learning","date":"2019-07-30","arxiv_id":"1907.12690","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-adversarial-inverse-reinforcement","slug":"multi-agent-adversarial-inverse-reinforcement","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","date":"2019-07-30","arxiv_id":"1907.13220","repositories_listed":1,"syntology":null},{"url":"/paper/reward-learning-for-efficient-reinforcement","slug":"reward-learning-for-efficient-reinforcement","title":"Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation","date":"2019-07-30","arxiv_id":"1907.12894","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/reward-learning-for-efficient-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12894"}},"official":{"repos":["UKPLab/ijcai2019-relis"],"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/action-grammars-a-cognitive-model-for","slug":"action-grammars-a-cognitive-model-for","title":"Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions","date":"2019-07-29","arxiv_id":"1907.12477","repositories_listed":1,"syntology":null},{"url":"/paper/minerl-a-large-scale-dataset-of-minecraft","slug":"minerl-a-large-scale-dataset-of-minecraft","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","date":"2019-07-29","arxiv_id":"1907.13440","repositories_listed":1,"syntology":null},{"url":"/paper/towards-model-based-reinforcement-learning","slug":"towards-model-based-reinforcement-learning","title":"Towards Model-based Reinforcement Learning for Industry-near Environments","date":"2019-07-27","arxiv_id":"1907.11971","repositories_listed":1,"syntology":null},{"url":"/paper/google-research-football-a-novel","slug":"google-research-football-a-novel","title":"Google Research Football: A Novel Reinforcement Learning Environment","date":"2019-07-25","arxiv_id":"1907.11180","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/google-research-football-a-novel#ran","syntology_url":"https://syntology.ai/paper/1907.11180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11180"}},"official":{"repos":["google-research/football"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discourse-marker-augmented-network-with-1","slug":"discourse-marker-augmented-network-with-1","title":"Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference","date":"2019-07-23","arxiv_id":"1907.09692","repositories_listed":1,"syntology":null},{"url":"/paper/metalearned-neural-memory","slug":"metalearned-neural-memory","title":"Metalearned Neural Memory","date":"2019-07-23","arxiv_id":"1907.09720","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-question-asking-using-neural-program","slug":"modeling-question-asking-using-neural-program","title":"Modeling question asking using neural program generation","date":"2019-07-23","arxiv_id":"1907.09899","repositories_listed":1,"syntology":null},{"url":"/paper/structured-fusion-networks-for-dialog","slug":"structured-fusion-networks-for-dialog","title":"Structured Fusion Networks for Dialog","date":"2019-07-23","arxiv_id":"1907.10016","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-attacks-on-deep-reinforcement","slug":"characterizing-attacks-on-deep-reinforcement","title":"Characterizing Attacks on Deep Reinforcement Learning","date":"2019-07-21","arxiv_id":"1907.09470","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/characterizing-attacks-on-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.09470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09470"}},"official":null}},{"url":"/paper/convolutional-reservoir-computing-for-world","slug":"convolutional-reservoir-computing-for-world","title":"Convolutional Reservoir Computing for World Models","date":"2019-07-18","arxiv_id":"1907.08040","repositories_listed":1,"syntology":null},{"url":"/paper/credit-assignment-as-a-proxy-for-transfer-in","slug":"credit-assignment-as-a-proxy-for-transfer-in","title":"Self-Attentional Credit Assignment for Transfer in Reinforcement Learning","date":"2019-07-18","arxiv_id":"1907.08027","repositories_listed":1,"syntology":null},{"url":"/paper/ppo-dash-improving-generalization-in-deep","slug":"ppo-dash-improving-generalization-in-deep","title":"PPO Dash: Improving Generalization in Deep Reinforcement Learning","date":"2019-07-15","arxiv_id":"1907.06704","repositories_listed":1,"syntology":null},{"url":"/paper/finite-time-performance-bounds-and-adaptive","slug":"finite-time-performance-bounds-and-adaptive","title":"Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning","date":"2019-07-14","arxiv_id":"1907.06290","repositories_listed":1,"syntology":null},{"url":"/paper/learning-self-correctable-policies-and-value","slug":"learning-self-correctable-policies-and-value","title":"Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling","date":"2019-07-12","arxiv_id":"1907.05634","repositories_listed":1,"syntology":null},{"url":"/paper/regularizing-neural-networks-for-future","slug":"regularizing-neural-networks-for-future","title":"Regularizing Neural Networks for Future Trajectory Prediction via Inverse Reinforcement Learning Framework","date":"2019-07-10","arxiv_id":"1907.04525","repositories_listed":1,"syntology":null},{"url":"/paper/striving-for-simplicity-in-off-policy-deep","slug":"striving-for-simplicity-in-off-policy-deep","title":"An Optimistic Perspective on Offline Reinforcement Learning","date":"2019-07-10","arxiv_id":"1907.04543","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-multi-task-deep-reinforcement","slug":"attentive-multi-task-deep-reinforcement","title":"Attentive Multi-Task Deep Reinforcement Learning","date":"2019-07-05","arxiv_id":"1907.02874","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/attentive-multi-task-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.02874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02874"}},"official":{"repos":["braemt/attentive-multi-task-deep-reinforcement-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/reasoning-and-generalization-in-rl-a-tool-use","slug":"reasoning-and-generalization-in-rl-a-tool-use","title":"Reasoning and Generalization in RL: A Tool Use Perspective","date":"2019-07-03","arxiv_id":"1907.02050","repositories_listed":1,"syntology":null},{"url":"/paper/conservative-q-improvement-reinforcement","slug":"conservative-q-improvement-reinforcement","title":"Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy","date":"2019-07-02","arxiv_id":"1907.01180","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/conservative-q-improvement-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.01180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01180"}},"official":null}},{"url":"/paper/detecting-spiky-corruption-in-markov-decision","slug":"detecting-spiky-corruption-in-markov-decision","title":"Detecting Spiky Corruption in Markov Decision Processes","date":"2019-06-30","arxiv_id":"1907.00452","repositories_listed":1,"syntology":null},{"url":"/paper/multiple-landmark-detection-using-multi-agent","slug":"multiple-landmark-detection-using-multi-agent","title":"Multiple Landmark Detection using Multi-Agent Reinforcement Learning","date":"2019-06-30","arxiv_id":"1907.00318","repositories_listed":1,"syntology":null},{"url":"/paper/variational-quantum-circuits-and-deep","slug":"variational-quantum-circuits-and-deep","title":"Variational Quantum Circuits for Deep Reinforcement Learning","date":"2019-06-30","arxiv_id":"1907.00397","repositories_listed":1,"syntology":null},{"url":"/paper/way-off-policy-batch-deep-reinforcement","slug":"way-off-policy-batch-deep-reinforcement","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","date":"2019-06-30","arxiv_id":"1907.00456","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/way-off-policy-batch-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.00456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00456"}},"official":{"repos":["natashamjaques/neural_chat"],"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/growing-action-spaces","slug":"growing-action-spaces","title":"Growing Action Spaces","date":"2019-06-28","arxiv_id":"1906.12266","repositories_listed":1,"syntology":null},{"url":"/paper/hyp-rl-hyperparameter-optimization-by","slug":"hyp-rl-hyperparameter-optimization-by","title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","date":"2019-06-27","arxiv_id":"1906.11527","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hyp-rl-hyperparameter-optimization-by#ran","syntology_url":"https://syntology.ai/paper/1906.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11527"}},"official":{"repos":["hadijomaa/HypRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-based-model-predictive-control-for-1","slug":"learning-based-model-predictive-control-for-1","title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","date":"2019-06-27","arxiv_id":"1906.12189","repositories_listed":1,"syntology":null},{"url":"/paper/cooperation-aware-reinforcement-learning-for","slug":"cooperation-aware-reinforcement-learning-for","title":"Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic","date":"2019-06-26","arxiv_id":"1906.11021","repositories_listed":1,"syntology":null},{"url":"/paper/pyrep-bringing-v-rep-to-deep-robot-learning","slug":"pyrep-bringing-v-rep-to-deep-robot-learning","title":"PyRep: Bringing V-REP to Deep Robot Learning","date":"2019-06-26","arxiv_id":"1906.11176","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-distilled-evolutionary-reinforcement","slug":"proximal-distilled-evolutionary-reinforcement","title":"Proximal Distilled Evolutionary Reinforcement Learning","date":"2019-06-24","arxiv_id":"1906.09807","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/proximal-distilled-evolutionary-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1906.09807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09807"}},"official":{"repos":["crisbodnar/pderl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-neurally-plausible-model-learns-successor","slug":"a-neurally-plausible-model-learns-successor","title":"A neurally plausible model learns successor representations in partially observable environments","date":"2019-06-22","arxiv_id":"1906.09480","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-neurally-plausible-model-learns-successor#ran","syntology_url":"https://syntology.ai/paper/1906.09480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09480"}},"official":{"repos":["evertes/distributional_SF"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/reinforcement-learning-with-convex","slug":"reinforcement-learning-with-convex","title":"Reinforcement Learning with Convex Constraints","date":"2019-06-21","arxiv_id":"1906.09323","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-convex#ran","syntology_url":"https://syntology.ai/paper/1906.09323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09323"}},"official":{"repos":["xkianteb/ApproPO"],"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/split-q-learning-reinforcement-learning-with","slug":"split-q-learning-reinforcement-learning-with","title":"Split Q Learning: Reinforcement Learning with Two-Stream Rewards","date":"2019-06-21","arxiv_id":"1906.12350","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-approach-for-1","slug":"a-deep-reinforcement-learning-approach-for-1","title":"A Deep Reinforcement Learning Approach for Global Routing","date":"2019-06-20","arxiv_id":"1906.08809","repositories_listed":1,"syntology":null},{"url":"/paper/calibrated-model-based-deep-reinforcement","slug":"calibrated-model-based-deep-reinforcement","title":"Calibrated Model-Based Deep Reinforcement Learning","date":"2019-06-19","arxiv_id":"1906.08312","repositories_listed":1,"syntology":null},{"url":"/paper/learning-driven-exploration-for-reinforcement","slug":"learning-driven-exploration-for-reinforcement","title":"Learning-Driven Exploration for Reinforcement Learning","date":"2019-06-17","arxiv_id":"1906.06890","repositories_listed":1,"syntology":null},{"url":"/paper/search-on-the-replay-buffer-bridging-planning","slug":"search-on-the-replay-buffer-bridging-planning","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","date":"2019-06-12","arxiv_id":"1906.05253","repositories_listed":1,"syntology":null},{"url":"/paper/causal-discovery-with-reinforcement-learning","slug":"causal-discovery-with-reinforcement-learning","title":"Causal Discovery with Reinforcement Learning","date":"2019-06-11","arxiv_id":"1906.04477","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-channel-coding","slug":"reinforcement-learning-for-channel-coding","title":"Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding","date":"2019-06-11","arxiv_id":"1906.04448","repositories_listed":1,"syntology":null},{"url":"/paper/wasserstein-reinforcement-learning","slug":"wasserstein-reinforcement-learning","title":"Learning to Score Behaviors for Guided Policy Optimization","date":"2019-06-11","arxiv_id":"1906.04349","repositories_listed":1,"syntology":null},{"url":"/paper/exploration-via-hindsight-goal-generation","slug":"exploration-via-hindsight-goal-generation","title":"Exploration via Hindsight Goal Generation","date":"2019-06-10","arxiv_id":"1906.04279","repositories_listed":1,"syntology":null},{"url":"/paper/neural-keyphrase-generation-via-reinforcement","slug":"neural-keyphrase-generation-via-reinforcement","title":"Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards","date":"2019-06-10","arxiv_id":"1906.04106","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/neural-keyphrase-generation-via-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1906.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04106"}},"official":{"repos":["kenchan0226/keyphrase-generation-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/curiosity-driven-multi-criteria-hindsight","slug":"curiosity-driven-multi-criteria-hindsight","title":"Curiosity-Driven Multi-Criteria Hindsight Experience Replay","date":"2019-06-09","arxiv_id":"1906.03710","repositories_listed":1,"syntology":null},{"url":"/paper/gossip-based-actor-learner-architectures-for","slug":"gossip-based-actor-learner-architectures-for","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","date":"2019-06-09","arxiv_id":"1906.04585","repositories_listed":1,"syntology":null},{"url":"/paper/preference-based-interactive-multi-document","slug":"preference-based-interactive-multi-document","title":"Preference-based Interactive Multi-Document Summarisation","date":"2019-06-07","arxiv_id":"1906.02923","repositories_listed":1,"syntology":null},{"url":"/paper/towards-interpretable-reinforcement-learning","slug":"towards-interpretable-reinforcement-learning","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","date":"2019-06-06","arxiv_id":"1906.02500","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-when-all-actions-are","slug":"reinforcement-learning-when-all-actions-are","title":"Reinforcement Learning When All Actions are Not Always Available","date":"2019-06-05","arxiv_id":"1906.01772","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-low-complexity","slug":"reinforcement-learning-with-low-complexity","title":"Reinforcement Learning with Low-Complexity Liquid State Machines","date":"2019-06-04","arxiv_id":"1906.01695","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reinforcement-learning-with-low-complexity#ran","syntology_url":"https://syntology.ai/paper/1906.01695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01695"}},"official":{"repos":["wponghiran/lsm-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-exploration-in-linear-quadratic","slug":"robust-exploration-in-linear-quadratic","title":"Robust exploration in linear quadratic reinforcement learning","date":"2019-06-04","arxiv_id":"1906.01584","repositories_listed":1,"syntology":null},{"url":"/paper/190600422","slug":"190600422","title":"On the Correctness and Sample Complexity of Inverse Reinforcement Learning","date":"2019-06-02","arxiv_id":"1906.00422","repositories_listed":1,"syntology":null},{"url":"/paper/190600214","slug":"190600214","title":"Harnessing Reinforcement Learning for Neural Motion Planning","date":"2019-06-01","arxiv_id":"1906.00214","repositories_listed":1,"syntology":null},{"url":"/paper/extending-deep-model-predictive-control-with","slug":"extending-deep-model-predictive-control-with","title":"Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks","date":"2019-05-31","arxiv_id":"1905.13402","repositories_listed":1,"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/extending-deep-model-predictive-control-with#ran","syntology_url":"https://syntology.ai/paper/1905.13402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13402"}},"official":null}},{"url":"/paper/interval-timing-in-deep-reinforcement","slug":"interval-timing-in-deep-reinforcement","title":"Interval timing in deep reinforcement learning agents","date":"2019-05-31","arxiv_id":"1905.13469","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-modeling-of-temporal-credit","slug":"sequence-modeling-of-temporal-credit","title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning","date":"2019-05-31","arxiv_id":"1905.13420","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/sequence-modeling-of-temporal-credit#ran","syntology_url":"https://syntology.ai/paper/1905.13420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13420"}},"official":null}},{"url":"/paper/reinforcement-learning-and-adaptive-sampling","slug":"reinforcement-learning-and-adaptive-sampling","title":"Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation","date":"2019-05-30","arxiv_id":"1905.12799","repositories_listed":1,"syntology":null},{"url":"/paper/towards-finding-longer-proofs","slug":"towards-finding-longer-proofs","title":"Towards Finding Longer Proofs","date":"2019-05-30","arxiv_id":"1905.13100","repositories_listed":1,"syntology":null},{"url":"/paper/190513547","slug":"190513547","title":"Learning robust control for LQR systems with multiplicative noise via policy gradient","date":"2019-05-28","arxiv_id":"1905.13547","repositories_listed":1,"syntology":null},{"url":"/paper/coordinated-exploration-via-intrinsic-rewards","slug":"coordinated-exploration-via-intrinsic-rewards","title":"Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning","date":"2019-05-28","arxiv_id":"1905.12127","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/coordinated-exploration-via-intrinsic-rewards#ran","syntology_url":"https://syntology.ai/paper/1905.12127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12127"}},"official":{"repos":["shariqiqbal2810/Multi-Explore"],"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/snooping-attacks-on-deep-reinforcement","slug":"snooping-attacks-on-deep-reinforcement","title":"Snooping Attacks on Deep Reinforcement Learning","date":"2019-05-28","arxiv_id":"1905.11832","repositories_listed":1,"syntology":null}],"record_sha256":"ba3bdad556d995f5daaa6760e59a0921a2d6ab559291a0322d410eb09c283427","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}