{"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/38","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":38,"pages_in_order":135,"rows_per_page":100,"rows":[3701,3800],"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/37","next":"/task/reinforcement-learning-2/papers/39","papers":[{"url":"/paper/finite-time-analysis-of-q-learning-with","slug":"finite-time-analysis-of-q-learning-with","title":"Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning","date":"2019-05-27","arxiv_id":"1905.11425","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finite-time-analysis-of-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/1905.11425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11425"}},"official":null}},{"url":"/paper/learning-to-discretize-solving-1d-scalar","slug":"learning-to-discretize-solving-1d-scalar","title":"Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning","date":"2019-05-27","arxiv_id":"1905.11079","repositories_listed":1,"syntology":null},{"url":"/paper/tight-regret-bounds-for-model-based","slug":"tight-regret-bounds-for-model-based","title":"Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies","date":"2019-05-27","arxiv_id":"1905.11527","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tight-regret-bounds-for-model-based#ran","syntology_url":"https://syntology.ai/paper/1905.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11527"}},"official":{"repos":["NMerlis/TabulaRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-via-online","slug":"safe-reinforcement-learning-via-online","title":"Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding","date":"2019-05-25","arxiv_id":"1905.10691","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-symmetric-reward-noising-for","slug":"adaptive-symmetric-reward-noising-for","title":"Adaptive Symmetric Reward Noising for Reinforcement Learning","date":"2019-05-24","arxiv_id":"1905.10144","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-for-1","slug":"hierarchical-reinforcement-learning-for-1","title":"Hierarchical Reinforcement Learning for Concurrent Discovery of Compound and Composable Policies","date":"2019-05-23","arxiv_id":"1905.09668","repositories_listed":1,"syntology":null},{"url":"/paper/multi-hop-reading-comprehension-via-deep","slug":"multi-hop-reading-comprehension-via-deep","title":"Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal","date":"2019-05-23","arxiv_id":"1905.09438","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-based-parameter","slug":"deep-reinforcement-learning-based-parameter","title":"Deep Reinforcement Learning Based Parameter Control in Differential Evolution","date":"2019-05-20","arxiv_id":"1905.08006","repositories_listed":1,"syntology":null},{"url":"/paper/a-regularized-opponent-model-with-maximum","slug":"a-regularized-opponent-model-with-maximum","title":"A Regularized Opponent Model with Maximum Entropy Objective","date":"2019-05-17","arxiv_id":"1905.08087","repositories_listed":1,"syntology":null},{"url":"/paper/exact-k-recommendation-via-maximal-clique","slug":"exact-k-recommendation-via-maximal-clique","title":"Exact-K Recommendation via Maximal Clique Optimization","date":"2019-05-17","arxiv_id":"1905.07089","repositories_listed":1,"syntology":null},{"url":"/paper/mastering-the-game-of-sungka-from-random-play","slug":"mastering-the-game-of-sungka-from-random-play","title":"Mastering the Game of Sungka from Random Play","date":"2019-05-17","arxiv_id":"1905.07102","repositories_listed":1,"syntology":null},{"url":"/paper/qbso-fs-a-reinforcement-learning-based-bee","slug":"qbso-fs-a-reinforcement-learning-based-bee","title":"QBSO-FS: A Reinforcement Learning Based Bee Swarm Optimization Metaheuristic for Feature Selection","date":"2019-05-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/expressive-priors-in-bayesian-neural-networks","slug":"expressive-priors-in-bayesian-neural-networks","title":"Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions","date":"2019-05-15","arxiv_id":"1905.06076","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/expressive-priors-in-bayesian-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1905.06076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.06076"}},"official":null}},{"url":"/paper/meta-reinforcement-learning-as-task-inference","slug":"meta-reinforcement-learning-as-task-inference","title":"Meta reinforcement learning as task inference","date":"2019-05-15","arxiv_id":"1905.06424","repositories_listed":1,"syntology":null},{"url":"/paper/control-regularization-for-reduced-variance","slug":"control-regularization-for-reduced-variance","title":"Control Regularization for Reduced Variance Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05380","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/control-regularization-for-reduced-variance#ran","syntology_url":"https://syntology.ai/paper/1905.05380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05380"}},"official":{"repos":["rcheng805/CORE-RL"],"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/successor-options-an-option-discovery","slug":"successor-options-an-option-discovery","title":"Successor Options: An Option Discovery Framework for Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05731","repositories_listed":1,"syntology":null},{"url":"/paper/cityflow-a-multi-agent-reinforcement-learning","slug":"cityflow-a-multi-agent-reinforcement-learning","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","date":"2019-05-13","arxiv_id":"1905.05217","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/cityflow-a-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1905.05217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05217"}},"official":{"repos":["cityflow-project/CityFlow"],"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/multi-agent-image-classification-via","slug":"multi-agent-image-classification-via","title":"Multi-Agent Image Classification via Reinforcement Learning","date":"2019-05-13","arxiv_id":"1905.04835","repositories_listed":1,"syntology":null},{"url":"/paper/task-agnostic-dynamics-priors-for-deep","slug":"task-agnostic-dynamics-priors-for-deep","title":"Task-Agnostic Dynamics Priors for Deep Reinforcement Learning","date":"2019-05-13","arxiv_id":"1905.04819","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/task-agnostic-dynamics-priors-for-deep#ran","syntology_url":"https://syntology.ai/paper/1905.04819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04819"}},"official":{"repos":["yilundu/task_agnostic_dynamics_prior"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/autonomous-management-of-energy-harvesting","slug":"autonomous-management-of-energy-harvesting","title":"Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning","date":"2019-05-10","arxiv_id":"1905.04181","repositories_listed":1,"syntology":null},{"url":"/paper/190503389","slug":"190503389","title":"Learning to Evolve","date":"2019-05-08","arxiv_id":"1905.03389","repositories_listed":1,"syntology":null},{"url":"/paper/dimension-wise-importance-sampling-weight","slug":"dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","arxiv_id":"1905.02363","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":18,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dimension-wise-importance-sampling-weight#ran","syntology_url":"https://syntology.ai/paper/1905.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02363"}},"official":{"repos":["seungyulhan/disc"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-ordinal-reinforcement-learning","slug":"deep-ordinal-reinforcement-learning","title":"Deep Ordinal Reinforcement Learning","date":"2019-05-06","arxiv_id":"1905.02005","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-control-in-metric-space-with","slug":"learning-to-control-in-metric-space-with","title":"Learning to Control in Metric Space with Optimal Regret","date":"2019-05-05","arxiv_id":"1905.01576","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/learning-to-control-in-metric-space-with#ran","syntology_url":"https://syntology.ai/paper/1905.01576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.01576"}},"official":null}},{"url":"/paper/the-game-of-tetris-in-machine-learning","slug":"the-game-of-tetris-in-machine-learning","title":"The Game of Tetris in Machine Learning","date":"2019-05-05","arxiv_id":"1905.01652","repositories_listed":1,"syntology":null},{"url":"/paper/deep-residual-reinforcement-learning","slug":"deep-residual-reinforcement-learning","title":"Deep Residual Reinforcement Learning","date":"2019-05-03","arxiv_id":"1905.01072","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-evolutionary-reinforcement","slug":"collaborative-evolutionary-reinforcement","title":"Collaborative Evolutionary Reinforcement Learning","date":"2019-05-02","arxiv_id":"1905.00976","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/collaborative-evolutionary-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1905.00976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00976"}},"official":{"repos":["intelai/cerl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-model-free-reinforcement-learning-1","slug":"efficient-model-free-reinforcement-learning-1","title":"Efficient Model-free Reinforcement Learning in Metric Spaces","date":"2019-05-01","arxiv_id":"1905.00475","repositories_listed":1,"syntology":null},{"url":"/paper/challenges-of-real-world-reinforcement","slug":"challenges-of-real-world-reinforcement","title":"Challenges of Real-World Reinforcement Learning","date":"2019-04-29","arxiv_id":"1904.12901","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-time-mean-variance-portfolio","slug":"continuous-time-mean-variance-portfolio","title":"Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework","date":"2019-04-25","arxiv_id":"1904.11392","repositories_listed":1,"syntology":null},{"url":"/paper/neural-logic-reinforcement-learning","slug":"neural-logic-reinforcement-learning","title":"Neural Logic Reinforcement Learning","date":"2019-04-24","arxiv_id":"1904.10729","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/neural-logic-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1904.10729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10729"}},"official":{"repos":["ZhengyaoJiang/NLRL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/graphnas-graph-neural-architecture-search","slug":"graphnas-graph-neural-architecture-search","title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","date":"2019-04-22","arxiv_id":"1904.09981","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/graphnas-graph-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1904.09981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09981"}},"official":{"repos":["GraphNAS/GraphNAS-simple"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/the-minerl-competition-on-sample-efficient","slug":"the-minerl-competition-on-sample-efficient","title":"The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors","date":"2019-04-22","arxiv_id":"1904.10079","repositories_listed":1,"syntology":null},{"url":"/paper/lets-play-again-variability-of-deep","slug":"lets-play-again-variability-of-deep","title":"Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments","date":"2019-04-12","arxiv_id":"1904.06312","repositories_listed":1,"syntology":null},{"url":"/paper/reinbo-machine-learning-pipeline-search-and","slug":"reinbo-machine-learning-pipeline-search-and","title":"ReinBo: Machine Learning pipeline search and configuration with Bayesian Optimization embedded Reinforcement Learning","date":"2019-04-10","arxiv_id":"1904.05381","repositories_listed":1,"syntology":null},{"url":"/paper/jointly-pre-training-with-supervised","slug":"jointly-pre-training-with-supervised","title":"Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning","date":"2019-04-03","arxiv_id":"1904.02206","repositories_listed":1,"syntology":null},{"url":"/paper/dynamically-optimal-treatment-allocation","slug":"dynamically-optimal-treatment-allocation","title":"Dynamically Optimal Treatment Allocation","date":"2019-04-01","arxiv_id":"1904.01047","repositories_listed":1,"syntology":null},{"url":"/paper/autoregressive-policies-for-continuous","slug":"autoregressive-policies-for-continuous","title":"Autoregressive Policies for Continuous Control Deep Reinforcement Learning","date":"2019-03-27","arxiv_id":"1903.11524","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-off-policy-actor-critic","slug":"generalized-off-policy-actor-critic","title":"Generalized Off-Policy Actor-Critic","date":"2019-03-27","arxiv_id":"1903.11329","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-thermodynamic-trajectories-using","slug":"optimizing-thermodynamic-trajectories-using","title":"Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning","date":"2019-03-20","arxiv_id":"1903.08543","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-agent-off-policy-actor-critic","slug":"a-multi-agent-off-policy-actor-critic","title":"A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","date":"2019-03-15","arxiv_id":"1903.06372","repositories_listed":1,"syntology":null},{"url":"/paper/gym-gazebo2-a-toolkit-for-reinforcement","slug":"gym-gazebo2-a-toolkit-for-reinforcement","title":"gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo","date":"2019-03-14","arxiv_id":"1903.06278","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-dynamic-boltzmann","slug":"reinforcement-learning-with-dynamic-boltzmann","title":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates","date":"2019-03-14","arxiv_id":"1903.05926","repositories_listed":1,"syntology":null},{"url":"/paper/coacor-code-annotation-for-code-retrieval","slug":"coacor-code-annotation-for-code-retrieval","title":"CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning","date":"2019-03-13","arxiv_id":"1904.00720","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/coacor-code-annotation-for-code-retrieval#ran","syntology_url":"https://syntology.ai/paper/1904.00720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00720"}},"official":{"repos":["LittleYUYU/CoaCor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/vrkitchen-an-interactive-3d-virtual","slug":"vrkitchen-an-interactive-3d-virtual","title":"VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning","date":"2019-03-13","arxiv_id":"1903.05757","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-reinforcement-learning-with-expert","slug":"hybrid-reinforcement-learning-with-expert","title":"Hybrid Reinforcement Learning with Expert State Sequences","date":"2019-03-11","arxiv_id":"1903.04110","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/hybrid-reinforcement-learning-with-expert#ran","syntology_url":"https://syntology.ai/paper/1903.04110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04110"}},"official":{"repos":["XiaoxiaoGuo/tensor4rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-deep-reinforcement-learning-for-2","slug":"multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","arxiv_id":"1903.04527","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-agent-deep-reinforcement-learning-for-2#ran","syntology_url":"https://syntology.ai/paper/1903.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04527"}},"official":{"repos":["cts198859/deeprl_signal_control"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-model-free-reinforcement","slug":"sample-efficient-model-free-reinforcement","title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","date":"2019-03-11","arxiv_id":"1903.04193","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-power-system-emergency-control-using","slug":"adaptive-power-system-emergency-control-using","title":"Adaptive Power System Emergency Control using Deep Reinforcement Learning","date":"2019-03-09","arxiv_id":"1903.03712","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-power-system-emergency-control-using#ran","syntology_url":"https://syntology.ai/paper/1903.03712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03712"}},"official":{"repos":["RLGC-Project/RLGC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/concurrent-meta-reinforcement-learning","slug":"concurrent-meta-reinforcement-learning","title":"Concurrent Meta Reinforcement Learning","date":"2019-03-07","arxiv_id":"1903.02710","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-research-trends-from-arxiv","slug":"predicting-research-trends-from-arxiv","title":"Predicting Research Trends From Arxiv","date":"2019-03-07","arxiv_id":"1903.02831","repositories_listed":1,"syntology":null},{"url":"/paper/a-hitchhiker-s-guide-to-statistical","slug":"a-hitchhiker-s-guide-to-statistical","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","date":"2019-03-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/simple-rl-reproducible-reinforcement-learning","slug":"simple-rl-reproducible-reinforcement-learning","title":"simple_rl: Reproducible Reinforcement Learning in Python","date":"2019-03-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-natural-language-for-reward-shaping-in","slug":"using-natural-language-for-reward-shaping-in","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","date":"2019-03-05","arxiv_id":"1903.02020","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/using-natural-language-for-reward-shaping-in#ran","syntology_url":"https://syntology.ai/paper/1903.02020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02020"}},"official":null}},{"url":"/paper/viewpoint-optimization-for-autonomous","slug":"viewpoint-optimization-for-autonomous","title":"Viewpoint Optimization for Autonomous Strawberry Harvesting with Deep Reinforcement Learning","date":"2019-03-05","arxiv_id":"1903.02074","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-actor-critic-reinforcement-learning-in","slug":"hybrid-actor-critic-reinforcement-learning-in","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","date":"2019-03-04","arxiv_id":"1903.01344","repositories_listed":1,"syntology":null},{"url":"/paper/model-primitive-hierarchical-lifelong","slug":"model-primitive-hierarchical-lifelong","title":"Model Primitive Hierarchical Lifelong Reinforcement Learning","date":"2019-03-04","arxiv_id":"1903.01567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-primitive-hierarchical-lifelong#ran","syntology_url":"https://syntology.ai/paper/1903.01567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.01567"}},"official":{"repos":["sisl/MPHRL"],"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/scaling-up-budgeted-reinforcement-learning","slug":"scaling-up-budgeted-reinforcement-learning","title":"Budgeted Reinforcement Learning in Continuous State Space","date":"2019-03-03","arxiv_id":"1903.01004","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reinforcement-learning-with-a-mind","slug":"efficient-reinforcement-learning-with-a-mind","title":"Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning","date":"2019-03-02","arxiv_id":"1903.00715","repositories_listed":1,"syntology":null},{"url":"/paper/regularity-normalization-constraining","slug":"regularity-normalization-constraining","title":"Unsupervised Attention Mechanism across Neural Network Layers","date":"2019-02-27","arxiv_id":"1902.10658","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-bottlenecks-in-deep-q-learning","slug":"diagnosing-bottlenecks-in-deep-q-learning","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","date":"2019-02-26","arxiv_id":"1902.10250","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diagnosing-bottlenecks-in-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1902.10250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10250"}},"official":null}},{"url":"/paper/flappy-hummingbird-an-open-source-dynamic","slug":"flappy-hummingbird-an-open-source-dynamic","title":"Flappy Hummingbird: An Open Source Dynamic Simulation of Flapping Wing Robots and Animals","date":"2019-02-25","arxiv_id":"1902.09628","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-confidence-regions-tight-bayesian","slug":"beyond-confidence-regions-tight-bayesian","title":"Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs","date":"2019-02-20","arxiv_id":"1902.07605","repositories_listed":1,"syntology":null},{"url":"/paper/hyperbolic-discounting-and-learning-over","slug":"hyperbolic-discounting-and-learning-over","title":"Hyperbolic Discounting and Learning over Multiple Horizons","date":"2019-02-19","arxiv_id":"1902.06865","repositories_listed":1,"syntology":null},{"url":"/paper/prolonets-neural-encoding-human-experts","slug":"prolonets-neural-encoding-human-experts","title":"Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning","date":"2019-02-15","arxiv_id":"1902.06007","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-visuomotor-control-through","slug":"unsupervised-visuomotor-control-through","title":"Unsupervised Visuomotor Control through Distributional Planning Networks","date":"2019-02-14","arxiv_id":"1902.05542","repositories_listed":1,"syntology":null},{"url":"/paper/verifiably-safe-off-model-reinforcement","slug":"verifiably-safe-off-model-reinforcement","title":"Verifiably Safe Off-Model Reinforcement Learning","date":"2019-02-14","arxiv_id":"1902.05632","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-through-simulation-integrating","slug":"generalization-through-simulation-integrating","title":"Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight","date":"2019-02-11","arxiv_id":"1902.03701","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/generalization-through-simulation-integrating#ran","syntology_url":"https://syntology.ai/paper/1902.03701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.03701"}},"official":{"repos":["gkahn13/GtS"],"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/artificial-intelligence-for-prosthetics","slug":"artificial-intelligence-for-prosthetics","title":"Artificial Intelligence for Prosthetics - challenge solutions","date":"2019-02-07","arxiv_id":"1902.02441","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/artificial-intelligence-for-prosthetics#ran","syntology_url":"https://syntology.ai/paper/1902.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.02441"}},"official":{"repos":["iasawseen/MultiServerRL"],"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/deeper-sparser-exploration","slug":"deeper-sparser-exploration","title":"Bayesian Reinforcement Learning via Deep, Sparse Sampling","date":"2019-02-07","arxiv_id":"1902.02661","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-schedule-communication-in-multi","slug":"learning-to-schedule-communication-in-multi","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","date":"2019-02-05","arxiv_id":"1902.01554","repositories_listed":1,"syntology":null},{"url":"/paper/the-natural-language-of-actions","slug":"the-natural-language-of-actions","title":"The Natural Language of Actions","date":"2019-02-04","arxiv_id":"1902.01119","repositories_listed":1,"syntology":null},{"url":"/paper/a-meta-mdp-approach-to-exploration-for","slug":"a-meta-mdp-approach-to-exploration-for","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","date":"2019-02-03","arxiv_id":"1902.00843","repositories_listed":1,"syntology":null},{"url":"/paper/certified-reinforcement-learning-with-logic","slug":"certified-reinforcement-learning-with-logic","title":"Certified Reinforcement Learning with Logic Guidance","date":"2019-02-02","arxiv_id":"1902.00778","repositories_listed":1,"syntology":null},{"url":"/paper/policy-consolidation-for-continual","slug":"policy-consolidation-for-continual","title":"Policy Consolidation for Continual Reinforcement Learning","date":"2019-02-01","arxiv_id":"1902.00255","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-consolidation-for-continual#ran","syntology_url":"https://syntology.ai/paper/1902.00255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00255"}},"official":null}},{"url":"/paper/contrasting-exploration-in-parameter-and","slug":"contrasting-exploration-in-parameter-and","title":"Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective","date":"2019-01-31","arxiv_id":"1901.11503","repositories_listed":1,"syntology":null},{"url":"/paper/private-q-learning-with-functional-noise-in","slug":"private-q-learning-with-functional-noise-in","title":"Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces","date":"2019-01-30","arxiv_id":"1901.10634","repositories_listed":1,"syntology":null},{"url":"/paper/safe-efficient-and-comfortable-velocity","slug":"safe-efficient-and-comfortable-velocity","title":"Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving","date":"2019-01-29","arxiv_id":"1902.00089","repositories_listed":1,"syntology":null},{"url":"/paper/causal-reasoning-from-meta-reinforcement","slug":"causal-reasoning-from-meta-reinforcement","title":"Causal Reasoning from Meta-reinforcement Learning","date":"2019-01-23","arxiv_id":"1901.08162","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/causal-reasoning-from-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1901.08162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08162"}},"official":null}},{"url":"/paper/understanding-multi-step-deep-reinforcement","slug":"understanding-multi-step-deep-reinforcement","title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target","date":"2019-01-22","arxiv_id":"1901.07510","repositories_listed":1,"syntology":null},{"url":"/paper/wall-e-an-efficient-reinforcement-learning","slug":"wall-e-an-efficient-reinforcement-learning","title":"WALL-E: An Efficient Reinforcement Learning Research Framework","date":"2019-01-18","arxiv_id":"1901.06086","repositories_listed":1,"syntology":null},{"url":"/paper/amplifying-the-imitation-effect-for","slug":"amplifying-the-imitation-effect-for","title":"Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution","date":"2019-01-17","arxiv_id":"1901.05856","repositories_listed":1,"syntology":null},{"url":"/paper/autophase-compiler-phase-ordering-for-high","slug":"autophase-compiler-phase-ordering-for-high","title":"AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning","date":"2019-01-15","arxiv_id":"1901.04615","repositories_listed":1,"syntology":null},{"url":"/paper/self-learning-exploration-and-mapping-for","slug":"self-learning-exploration-and-mapping-for","title":"Self-Learning Exploration and Mapping for Mobile Robots via Deep Reinforcement Learning","date":"2019-01-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-via","slug":"hierarchical-reinforcement-learning-via","title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","date":"2019-01-05","arxiv_id":"1901.01365","repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-user-model-for","slug":"generative-adversarial-user-model-for","title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System","date":"2018-12-27","arxiv_id":"1812.10613","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/generative-adversarial-user-model-for#ran","syntology_url":"https://syntology.ai/paper/1812.10613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.10613"}},"official":{"repos":["xinshi-chen/GenerativeAdversarialUserModel"],"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/deconfounding-reinforcement-learning-in","slug":"deconfounding-reinforcement-learning-in","title":"Deconfounding Reinforcement Learning in Observational Settings","date":"2018-12-26","arxiv_id":"1812.10576","repositories_listed":1,"syntology":null},{"url":"/paper/iroko-a-framework-to-prototype-reinforcement","slug":"iroko-a-framework-to-prototype-reinforcement","title":"Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control","date":"2018-12-24","arxiv_id":"1812.09975","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-with-non-expert-human","slug":"pre-training-with-non-expert-human","title":"Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning","date":"2018-12-21","arxiv_id":"1812.08904","repositories_listed":1,"syntology":null},{"url":"/paper/td-regularized-actor-critic-methods","slug":"td-regularized-actor-critic-methods","title":"TD-Regularized Actor-Critic Methods","date":"2018-12-19","arxiv_id":"1812.08288","repositories_listed":1,"syntology":null},{"url":"/paper/information-directed-exploration-for-deep","slug":"information-directed-exploration-for-deep","title":"Information-Directed Exploration for Deep Reinforcement Learning","date":"2018-12-18","arxiv_id":"1812.07544","repositories_listed":1,"syntology":null},{"url":"/paper/an-atari-model-zoo-for-analyzing-visualizing","slug":"an-atari-model-zoo-for-analyzing-visualizing","title":"An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents","date":"2018-12-17","arxiv_id":"1812.07069","repositories_listed":1,"syntology":null},{"url":"/paper/residual-policy-learning","slug":"residual-policy-learning","title":"Residual Policy Learning","date":"2018-12-15","arxiv_id":"1812.06298","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/residual-policy-learning#ran","syntology_url":"https://syntology.ai/paper/1812.06298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06298"}},"official":null}},{"url":"/paper/simulation-to-scaled-city-zero-shot-policy","slug":"simulation-to-scaled-city-zero-shot-policy","title":"Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles","date":"2018-12-14","arxiv_id":"1812.06120","repositories_listed":1,"syntology":null},{"url":"/paper/exploration-conscious-reinforcement-learning","slug":"exploration-conscious-reinforcement-learning","title":"Exploration Conscious Reinforcement Learning Revisited","date":"2018-12-13","arxiv_id":"1812.05551","repositories_listed":1,"syntology":null},{"url":"/paper/irlas-inverse-reinforcement-learning-for","slug":"irlas-inverse-reinforcement-learning-for","title":"IRLAS: Inverse Reinforcement Learning for Architecture Search","date":"2018-12-13","arxiv_id":"1812.05285","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-generation-from-imitation-learning","slug":"dialogue-generation-from-imitation-learning","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","date":"2018-12-09","arxiv_id":"1812.03509","repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-rehearsal-achieving-deep-reinforcement","slug":"pseudo-rehearsal-achieving-deep-reinforcement","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","date":"2018-12-06","arxiv_id":"1812.02464","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-generalization-in-reinforcement","slug":"quantifying-generalization-in-reinforcement","title":"Quantifying Generalization in Reinforcement Learning","date":"2018-12-06","arxiv_id":"1812.02341","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":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quantifying-generalization-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1812.02341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.02341"}},"official":{"repos":["openai/coinrun"],"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/adapting-auxiliary-losses-using-gradient","slug":"adapting-auxiliary-losses-using-gradient","title":"Adapting Auxiliary Losses Using Gradient Similarity","date":"2018-12-05","arxiv_id":"1812.02224","repositories_listed":1,"syntology":null}],"record_sha256":"f62f5aecf9389d421940b129930c166c380ffa790dbb746c7c6cec0ae3c61b70","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}