{"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/42","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":42,"pages_in_order":152,"rows_per_page":100,"rows":[4101,4200],"of":15113,"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","prev":"/task/reinforcement-learning-1/papers/41","next":"/task/reinforcement-learning-1/papers/43","papers":[{"url":"/paper/quantized-reinforcement-learning-quarl","slug":"quantized-reinforcement-learning-quarl","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","date":"2019-10-02","arxiv_id":"1910.01055","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":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/quantized-reinforcement-learning-quarl#ran","syntology_url":"https://syntology.ai/paper/1910.01055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01055"}},"official":{"repos":["harvard-edge/quarl"],"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/multiagent-rollout-algorithms-and","slug":"multiagent-rollout-algorithms-and","title":"Multiagent Rollout Algorithms and Reinforcement Learning","date":"2019-09-30","arxiv_id":"1910.00120","repositories_listed":1,"syntology":null},{"url":"/paper/relational-graph-learning-for-crowd","slug":"relational-graph-learning-for-crowd","title":"Relational Graph Learning for Crowd Navigation","date":"2019-09-28","arxiv_id":"1909.13165","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-roi-generation-for-video-object","slug":"adaptive-roi-generation-for-video-object","title":"Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning","date":"2019-09-27","arxiv_id":"1909.12482","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-data-driven-robotics","slug":"a-framework-for-data-driven-robotics","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","date":"2019-09-26","arxiv_id":"1909.12200","repositories_listed":1,"syntology":null},{"url":"/paper/a-simulation-of-uav-power-optimization-via","slug":"a-simulation-of-uav-power-optimization-via","title":"Visual Exploration and Energy-aware Path Planning via Reinforcement Learning","date":"2019-09-26","arxiv_id":"1909.12217","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-structures-for-value-based","slug":"harnessing-structures-for-value-based","title":"Harnessing Structures for Value-Based Planning and Reinforcement Learning","date":"2019-09-26","arxiv_id":"1909.12255","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/harnessing-structures-for-value-based#ran","syntology_url":"https://syntology.ai/paper/1909.12255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12255"}},"official":{"repos":["YyzHarry/SV-RL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rl-lim-reinforcement-learning-based-locally","slug":"rl-lim-reinforcement-learning-based-locally","title":"LIMIS: Locally Interpretable Modeling using Instance-wise Subsampling","date":"2019-09-26","arxiv_id":"1909.12367","repositories_listed":1,"syntology":null},{"url":"/paper/good-robot-efficient-reinforcement-learning","slug":"good-robot-efficient-reinforcement-learning","title":"\"Good Robot!\": Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer","date":"2019-09-25","arxiv_id":"1909.11730","repositories_listed":1,"syntology":null},{"url":"/paper/robel-robotics-benchmarks-for-learning-with","slug":"robel-robotics-benchmarks-for-learning-with","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","date":"2019-09-25","arxiv_id":"1909.11639","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-state-control-through","slug":"self-supervised-state-control-through","title":"Self-Supervised State-Control through Intrinsic Mutual Information Rewards","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/accept-synthetic-objects-as-real-end-to-end","slug":"accept-synthetic-objects-as-real-end-to-end","title":"Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Clutter","date":"2019-09-24","arxiv_id":"1909.11128","repositories_listed":1,"syntology":null},{"url":"/paper/avoidance-learning-using-observational","slug":"avoidance-learning-using-observational","title":"Avoidance Learning Using Observational Reinforcement Learning","date":"2019-09-24","arxiv_id":"1909.11228","repositories_listed":1,"syntology":null},{"url":"/paper/demystifying-active-inference","slug":"demystifying-active-inference","title":"Active inference: demystified and compared","date":"2019-09-24","arxiv_id":"1909.10863","repositories_listed":1,"syntology":null},{"url":"/paper/invariant-transform-experience-replay","slug":"invariant-transform-experience-replay","title":"Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning","date":"2019-09-24","arxiv_id":"1909.10707","repositories_listed":1,"syntology":null},{"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/predicting-optimal-value-functions-by","slug":"predicting-optimal-value-functions-by","title":"Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning","date":"2019-09-11","arxiv_id":"1909.05004","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/ac-teach-a-bayesian-actor-critic-method-for","slug":"ac-teach-a-bayesian-actor-critic-method-for","title":"AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers","date":"2019-09-09","arxiv_id":"1909.04121","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/ac-teach-a-bayesian-actor-critic-method-for#ran","syntology_url":"https://syntology.ai/paper/1909.04121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04121"}},"official":null}},{"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/learning-action-transferable-policy-with","slug":"learning-action-transferable-policy-with","title":"Learning Action-Transferable Policy with Action Embedding","date":"2019-09-05","arxiv_id":"1909.02291","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/no-press-diplomacy-modeling-multi-agent","slug":"no-press-diplomacy-modeling-multi-agent","title":"No Press Diplomacy: Modeling Multi-Agent Gameplay","date":"2019-09-04","arxiv_id":"1909.02128","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/no-press-diplomacy-modeling-multi-agent#ran","syntology_url":"https://syntology.ai/paper/1909.02128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02128"}},"official":{"repos":["diplomacy/research"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-build-user-simulators-to-train-rl","slug":"how-to-build-user-simulators-to-train-rl","title":"How to Build User Simulators to Train RL-based Dialog Systems","date":"2019-09-03","arxiv_id":"1909.01388","repositories_listed":1,"syntology":null},{"url":"/paper/generating-classical-chinese-poems-from","slug":"generating-classical-chinese-poems-from","title":"Generating Classical Chinese Poems from Vernacular Chinese","date":"2019-08-31","arxiv_id":"1909.00279","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/imitation-learning-for-sentence-generation","slug":"imitation-learning-for-sentence-generation","title":"Imitation Learning for Sentence Generation with Dilated Convolutions Using Adversarial Training","date":"2019-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/towards-diverse-and-accurate-image-captions","slug":"towards-diverse-and-accurate-image-captions","title":"Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process","date":"2019-08-14","arxiv_id":"1908.04919","repositories_listed":1,"syntology":null},{"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/doorgym-a-scalable-door-opening-environment","slug":"doorgym-a-scalable-door-opening-environment","title":"DoorGym: A Scalable Door Opening Environment And Baseline Agent","date":"2019-08-05","arxiv_id":"1908.01887","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/combining-learned-skills-and-reinforcement","slug":"combining-learned-skills-and-reinforcement","title":"Learning to combine primitive skills: A step towards versatile robotic manipulation","date":"2019-08-02","arxiv_id":"1908.00722","repositories_listed":1,"syntology":null},{"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/hindsight-trust-region-policy-optimization","slug":"hindsight-trust-region-policy-optimization","title":"Hindsight Trust Region Policy Optimization","date":"2019-07-29","arxiv_id":"1907.12439","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/environment-probing-interaction-policies-1","slug":"environment-probing-interaction-policies-1","title":"Environment Probing Interaction Policies","date":"2019-07-26","arxiv_id":"1907.11740","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/learning-how-to-active-learn-by-dreaming","slug":"learning-how-to-active-learn-by-dreaming","title":"Learning How to Active Learn by Dreaming","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-training-data-selection-for-domain","slug":"reinforced-training-data-selection-for-domain","title":"Reinforced Training Data Selection for Domain Adaptation","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":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/towards-empathic-deep-q-learning","slug":"towards-empathic-deep-q-learning","title":"Towards Empathic Deep Q-Learning","date":"2019-06-26","arxiv_id":"1906.10918","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/towards-empathic-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1906.10918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10918"}},"official":{"repos":["bartbussmann/EmpathicDQN"],"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"]}}}],"record_sha256":"50888bfde244027c547ae4e29ea3f079c931d48b61d8bbff5adaa22e3fcd6063","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}