{"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/34","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":34,"pages_in_order":152,"rows_per_page":100,"rows":[3301,3400],"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/33","next":"/task/reinforcement-learning-1/papers/35","papers":[{"url":"/paper/generating-multi-type-sequences-of-temporal","slug":"generating-multi-type-sequences-of-temporal","title":"Generating Multi-type Temporal Sequences to Mitigate Class-imbalanced Problem","date":"2021-04-07","arxiv_id":"2104.03428","repositories_listed":1,"syntology":null},{"url":"/paper/plasticinelab-a-soft-body-manipulation-1","slug":"plasticinelab-a-soft-body-manipulation-1","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","date":"2021-04-07","arxiv_id":"2104.03311","repositories_listed":1,"syntology":null},{"url":"/paper/design-and-implementation-of-an-environment","slug":"design-and-implementation-of-an-environment","title":"Design and implementation of an environment for Learning to Run a Power Network (L2RPN)","date":"2021-04-06","arxiv_id":"2104.04080","repositories_listed":1,"syntology":null},{"url":"/paper/c-coma-a-continual-reinforcement-learning","slug":"c-coma-a-continual-reinforcement-learning","title":"C-COMA: A CONTINUAL REINFORCEMENT LEARNING MODEL FOR DYNAMIC MULTIAGENT ENVIRONMENTS","date":"2021-04-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/influencing-reinforcement-learning-through","slug":"influencing-reinforcement-learning-through","title":"Influencing Reinforcement Learning through Natural Language Guidance","date":"2021-04-04","arxiv_id":"2104.01506","repositories_listed":1,"syntology":null},{"url":"/paper/how-are-learned-perception-based-controllers","slug":"how-are-learned-perception-based-controllers","title":"How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?","date":"2021-04-02","arxiv_id":"2104.00827","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-co-adaptation-of-algorithmic-and","slug":"identifying-co-adaptation-of-algorithmic-and","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","date":"2021-03-31","arxiv_id":"2103.17258","repositories_listed":1,"syntology":null},{"url":"/paper/simultaneous-navigation-and-construction","slug":"simultaneous-navigation-and-construction","title":"Simultaneous Navigation and Construction Benchmarking Environments","date":"2021-03-31","arxiv_id":"2103.16732","repositories_listed":1,"syntology":null},{"url":"/paper/lemgorl-an-open-source-benchmark-tool-to","slug":"lemgorl-an-open-source-benchmark-tool-to","title":"Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control","date":"2021-03-30","arxiv_id":"2103.16223","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-resource-1","slug":"deep-reinforcement-learning-for-resource-1","title":"Deep Reinforcement Learning for Resource Allocation in Business Processes","date":"2021-03-29","arxiv_id":"2104.00541","repositories_listed":1,"syntology":null},{"url":"/paper/robust-reinforcement-learning-under-model","slug":"robust-reinforcement-learning-under-model","title":"Robust Reinforcement Learning under model misspecification","date":"2021-03-29","arxiv_id":"2103.15370","repositories_listed":1,"syntology":null},{"url":"/paper/shaping-advice-in-deep-multi-agent","slug":"shaping-advice-in-deep-multi-agent","title":"Shaping Advice in Deep Multi-Agent Reinforcement Learning","date":"2021-03-29","arxiv_id":"2103.15941","repositories_listed":1,"syntology":null},{"url":"/paper/self-adaptive-torque-vectoring-controller","slug":"self-adaptive-torque-vectoring-controller","title":"Self-adaptive Torque Vectoring Controller Using Reinforcement Learning","date":"2021-03-27","arxiv_id":"2103.14892","repositories_listed":1,"syntology":null},{"url":"/paper/agent-with-warm-start-and-adaptive-dynamic","slug":"agent-with-warm-start-and-adaptive-dynamic","title":"Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound","date":"2021-03-26","arxiv_id":"2103.14502","repositories_listed":1,"syntology":null},{"url":"/paper/character-controllers-using-motion-vaes","slug":"character-controllers-using-motion-vaes","title":"Character Controllers Using Motion VAEs","date":"2021-03-26","arxiv_id":"2103.14274","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/character-controllers-using-motion-vaes#ran","syntology_url":"https://syntology.ai/paper/2103.14274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14274"}},"official":{"repos":["electronicarts/character-motion-vaes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/medselect-selective-labeling-for-medical","slug":"medselect-selective-labeling-for-medical","title":"MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning","date":"2021-03-26","arxiv_id":"2103.14339","repositories_listed":1,"syntology":null},{"url":"/paper/model-predictive-actor-critic-accelerating","slug":"model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.13842","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-predictive-actor-critic-accelerating#ran","syntology_url":"https://syntology.ai/paper/2103.13842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13842"}},"official":{"repos":["dnandha/mopac"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-explanation-with-multi-agent","slug":"counterfactual-explanation-with-multi-agent","title":"Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction","date":"2021-03-24","arxiv_id":"2103.12983","repositories_listed":1,"syntology":null},{"url":"/paper/policy-information-capacity-information","slug":"policy-information-capacity-information","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","date":"2021-03-23","arxiv_id":"2103.12726","repositories_listed":1,"syntology":null},{"url":"/paper/replacing-rewards-with-examples-example-based","slug":"replacing-rewards-with-examples-example-based","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","date":"2021-03-23","arxiv_id":"2103.12656","repositories_listed":1,"syntology":null},{"url":"/paper/provably-correct-optimization-and-exploration","slug":"provably-correct-optimization-and-exploration","title":"Provably Correct Optimization and Exploration with Non-linear Policies","date":"2021-03-22","arxiv_id":"2103.11559","repositories_listed":1,"syntology":null},{"url":"/paper/human-inspired-multi-agent-navigation-using","slug":"human-inspired-multi-agent-navigation-using","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","date":"2021-03-18","arxiv_id":"2103.10000","repositories_listed":1,"syntology":null},{"url":"/paper/a-practical-guide-to-multi-objective","slug":"a-practical-guide-to-multi-objective","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","date":"2021-03-17","arxiv_id":"2103.09568","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-reinforcement-learning-for-1","slug":"weakly-supervised-reinforcement-learning-for-1","title":"Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages","date":"2021-03-17","arxiv_id":"2103.09726","repositories_listed":1,"syntology":null},{"url":"/paper/inclined-quadrotor-landing-using-deep","slug":"inclined-quadrotor-landing-using-deep","title":"Inclined Quadrotor Landing using Deep Reinforcement Learning","date":"2021-03-16","arxiv_id":"2103.09043","repositories_listed":1,"syntology":null},{"url":"/paper/lyapunov-barrier-policy-optimization-1","slug":"lyapunov-barrier-policy-optimization-1","title":"Lyapunov Barrier Policy Optimization","date":"2021-03-16","arxiv_id":"2103.09230","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-band","slug":"deep-reinforcement-learning-for-band","title":"Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification","date":"2021-03-15","arxiv_id":"2103.08741","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-algorithms-from","slug":"reinforcement-learning-with-algorithms-from","title":"Reinforcement Learning with Algorithms from Probabilistic Structure Estimation","date":"2021-03-15","arxiv_id":"2103.08241","repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-reinforcement-learning-2","slug":"sample-efficient-reinforcement-learning-2","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","date":"2021-03-15","arxiv_id":"2103.08255","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-for-automated-test-case","slug":"transfer-learning-for-automated-test-case","title":"Transfer Learning for Automated Test Case Prioritization Using XCSF","date":"2021-03-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/solving-compositional-reinforcement-learning-1","slug":"solving-compositional-reinforcement-learning-1","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","date":"2021-03-13","arxiv_id":"2103.07607","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/solving-compositional-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2103.07607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07607"}},"official":{"repos":["IrisLi17/self-imitation-via-reduction"],"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/large-batch-simulation-for-deep-reinforcement-1","slug":"large-batch-simulation-for-deep-reinforcement-1","title":"Large Batch Simulation for Deep Reinforcement Learning","date":"2021-03-12","arxiv_id":"2103.07013","repositories_listed":1,"syntology":null},{"url":"/paper/a-quadratic-actor-network-for-model-free","slug":"a-quadratic-actor-network-for-model-free","title":"A Quadratic Actor Network for Model-Free Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06617","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-episodic-memory-for-deep","slug":"generalizable-episodic-memory-for-deep","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06469","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/generalizable-episodic-memory-for-deep#ran","syntology_url":"https://syntology.ai/paper/2103.06469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06469"}},"official":{"repos":["MouseHu/GEM"],"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/policy-search-with-rare-significant-events","slug":"policy-search-with-rare-significant-events","title":"Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with","date":"2021-03-11","arxiv_id":"2103.06846","repositories_listed":1,"syntology":null},{"url":"/paper/xdo-a-double-oracle-algorithm-for-extensive","slug":"xdo-a-double-oracle-algorithm-for-extensive","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","date":"2021-03-11","arxiv_id":"2103.06426","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xdo-a-double-oracle-algorithm-for-extensive#ran","syntology_url":"https://syntology.ai/paper/2103.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06426"}},"official":{"repos":["indylab/nxdo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/a-scavenger-hunt-for-service-robots","slug":"a-scavenger-hunt-for-service-robots","title":"A Scavenger Hunt for Service Robots","date":"2021-03-09","arxiv_id":"2103.05225","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-shrinking-for-referring-expression","slug":"iterative-shrinking-for-referring-expression","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","date":"2021-03-09","arxiv_id":"2103.05187","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-prototypical-1","slug":"reinforcement-learning-with-prototypical-1","title":"Reinforcement Learning with Prototypical Representations","date":"2021-03-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-ai-arena-a-framework-for-distributed","slug":"the-ai-arena-a-framework-for-distributed","title":"The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learning","date":"2021-03-09","arxiv_id":"2103.05737","repositories_listed":1,"syntology":null},{"url":"/paper/a-crash-course-on-reinforcement-learning","slug":"a-crash-course-on-reinforcement-learning","title":"A Crash Course on Reinforcement Learning","date":"2021-03-08","arxiv_id":"2103.04910","repositories_listed":1,"syntology":null},{"url":"/paper/behavior-from-the-void-unsupervised-active","slug":"behavior-from-the-void-unsupervised-active","title":"Behavior From the Void: Unsupervised Active Pre-Training","date":"2021-03-08","arxiv_id":"2103.04551","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/behavior-from-the-void-unsupervised-active#ran","syntology_url":"https://syntology.ai/paper/2103.04551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.04551"}},"official":{"repos":["rll-research/url_benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/comparing-popular-simulation-environments-in","slug":"comparing-popular-simulation-environments-in","title":"Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learning","date":"2021-03-08","arxiv_id":"2103.04616","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-versus-model-free-deep","slug":"model-based-versus-model-free-deep","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","date":"2021-03-08","arxiv_id":"2103.04909","repositories_listed":1,"syntology":null},{"url":"/paper/deepfreight-a-model-free-deep-reinforcement","slug":"deepfreight-a-model-free-deep-reinforcement","title":"DeepFreight: Integrating Deep Reinforcement Learning and Mixed Integer Programming for Multi-transfer Truck Freight Delivery","date":"2021-03-05","arxiv_id":"2103.03450","repositories_listed":1,"syntology":null},{"url":"/paper/learning-collision-free-and-torque-limited","slug":"learning-collision-free-and-torque-limited","title":"Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors","date":"2021-03-05","arxiv_id":"2103.03793","repositories_listed":1,"syntology":null},{"url":"/paper/lyapunov-regularized-reinforcement-learning","slug":"lyapunov-regularized-reinforcement-learning","title":"Lyapunov-Regularized Reinforcement Learning for Power System Transient Stability","date":"2021-03-05","arxiv_id":"2103.03869","repositories_listed":1,"syntology":null},{"url":"/paper/mambpo-sample-efficient-multi-robot","slug":"mambpo-sample-efficient-multi-robot","title":"MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models","date":"2021-03-05","arxiv_id":"2103.03662","repositories_listed":1,"syntology":null},{"url":"/paper/model-free-two-step-design-for-improving","slug":"model-free-two-step-design-for-improving","title":"Two-step reinforcement learning for model-free redesign of nonlinear optimal regulator","date":"2021-03-05","arxiv_id":"2103.03808","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-for-robust-fitting-a","slug":"unsupervised-learning-for-robust-fitting-a","title":"Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach","date":"2021-03-05","arxiv_id":"2103.03501","repositories_listed":1,"syntology":null},{"url":"/paper/conservative-optimistic-policy-optimization","slug":"conservative-optimistic-policy-optimization","title":"Conservative Optimistic Policy Optimization via Multiple Importance Sampling","date":"2021-03-04","arxiv_id":"2103.03307","repositories_listed":1,"syntology":null},{"url":"/paper/improving-computational-efficiency-in-visual","slug":"improving-computational-efficiency-in-visual","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","date":"2021-03-04","arxiv_id":"2103.02886","repositories_listed":1,"syntology":null},{"url":"/paper/learning-the-next-best-view-for-3d-point","slug":"learning-the-next-best-view-for-3d-point","title":"Learning the Next Best View for 3D Point Clouds via Topological Features","date":"2021-03-04","arxiv_id":"2103.02789","repositories_listed":1,"syntology":null},{"url":"/paper/foresee-then-evaluate-decomposing-value","slug":"foresee-then-evaluate-decomposing-value","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","date":"2021-03-03","arxiv_id":"2103.02225","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/foresee-then-evaluate-decomposing-value#ran","syntology_url":"https://syntology.ai/paper/2103.02225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.02225"}},"official":{"repos":["bluecontra/AAAI2021-VDFP"],"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/adversarial-environment-generation-for-1","slug":"adversarial-environment-generation-for-1","title":"Adversarial Environment Generation for Learning to Navigate the Web","date":"2021-03-02","arxiv_id":"2103.01991","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-urllc-data","slug":"deep-reinforcement-learning-for-urllc-data","title":"Deep Reinforcement Learning for URLLC data management on top of scheduled eMBB traffic","date":"2021-03-02","arxiv_id":"2103.01801","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-safe-reinforcement-learning-using","slug":"model-based-safe-reinforcement-learning-using","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","date":"2021-03-02","arxiv_id":"2103.01556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2103.01556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01556"}},"official":{"repos":["mahaitongdae/safe_exp_env"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-and-partially-observable-goal","slug":"hierarchical-and-partially-observable-goal","title":"Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph","date":"2021-03-01","arxiv_id":"2103.01350","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/hierarchical-and-partially-observable-goal#ran","syntology_url":"https://syntology.ai/paper/2103.01350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01350"}},"official":{"repos":["Xin-Ye-1/HRL-GRG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-importance-of-hyperparameter","slug":"on-the-importance-of-hyperparameter","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","date":"2021-02-26","arxiv_id":"2102.13651","repositories_listed":1,"syntology":null},{"url":"/paper/robot-navigation-in-a-crowd-by-integrating","slug":"robot-navigation-in-a-crowd-by-integrating","title":"Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planning","date":"2021-02-26","arxiv_id":"2102.13265","repositories_listed":1,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-via-multi","slug":"robust-deep-reinforcement-learning-via-multi","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","date":"2021-02-26","arxiv_id":"2102.13268","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-via-multi#ran","syntology_url":"https://syntology.ai/paper/2102.13268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13268"}},"official":{"repos":["BU-DEPEND-Lab/DRIBO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-probabilistic-interpretation-of-self-paced","slug":"a-probabilistic-interpretation-of-self-paced","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","date":"2021-02-25","arxiv_id":"2102.13176","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/a-probabilistic-interpretation-of-self-paced#ran","syntology_url":"https://syntology.ai/paper/2102.13176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13176"}},"official":{"repos":["psclklnk/self-paced-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modular-object-oriented-games-a-task","slug":"modular-object-oriented-games-a-task","title":"Modular Object-Oriented Games: A Task Framework for Reinforcement Learning, Psychology, and Neuroscience","date":"2021-02-25","arxiv_id":"2102.12616","repositories_listed":1,"syntology":null},{"url":"/paper/information-directed-reward-learning-for","slug":"information-directed-reward-learning-for","title":"Information Directed Reward Learning for Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12466","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/information-directed-reward-learning-for#ran","syntology_url":"https://syntology.ai/paper/2102.12466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12466"}},"official":{"repos":["david-lindner/idrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-based-deep-reinforcement-learning-for-1","slug":"memory-based-deep-reinforcement-learning-for-1","title":"Memory-based Deep Reinforcement Learning for POMDPs","date":"2021-02-24","arxiv_id":"2102.12344","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/memory-based-deep-reinforcement-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2102.12344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12344"}},"official":{"repos":["LinghengMeng/LSTM-TD3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modular-deep-reinforcement-learning-for","slug":"modular-deep-reinforcement-learning-for","title":"Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic","date":"2021-02-24","arxiv_id":"2102.12855","repositories_listed":1,"syntology":null},{"url":"/paper/psiphi-learning-reinforcement-learning-with","slug":"psiphi-learning-reinforcement-learning-with","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","date":"2021-02-24","arxiv_id":"2102.12560","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-multimodal-reinforcement-learning","slug":"exploiting-multimodal-reinforcement-learning","title":"Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation","date":"2021-02-22","arxiv_id":"2102.11387","repositories_listed":1,"syntology":null},{"url":"/paper/explore-the-context-optimal-data-collection","slug":"explore-the-context-optimal-data-collection","title":"Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models","date":"2021-02-22","arxiv_id":"2102.11394","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/explore-the-context-optimal-data-collection#ran","syntology_url":"https://syntology.ai/paper/2102.11394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11394"}},"official":null}},{"url":"/paper/exploring-supervised-and-unsupervised-rewards","slug":"exploring-supervised-and-unsupervised-rewards","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","date":"2021-02-22","arxiv_id":"2102.11403","repositories_listed":1,"syntology":null},{"url":"/paper/program-synthesis-guided-reinforcement","slug":"program-synthesis-guided-reinforcement","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","date":"2021-02-22","arxiv_id":"2102.11137","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/program-synthesis-guided-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2102.11137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11137"}},"official":{"repos":["yycdavid/program-synthesis-guided-rl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-prototypical","slug":"reinforcement-learning-with-prototypical","title":"Reinforcement Learning with Prototypical Representations","date":"2021-02-22","arxiv_id":"2102.11271","repositories_listed":1,"syntology":null},{"url":"/paper/accelerated-sim-to-real-deep-reinforcement","slug":"accelerated-sim-to-real-deep-reinforcement","title":"Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player","date":"2021-02-21","arxiv_id":"2102.10711","repositories_listed":1,"syntology":null},{"url":"/paper/decaying-clipping-range-in-proximal-policy","slug":"decaying-clipping-range-in-proximal-policy","title":"Decaying Clipping Range in Proximal Policy Optimization","date":"2021-02-20","arxiv_id":"2102.10456","repositories_listed":1,"syntology":null},{"url":"/paper/towards-automatic-evaluation-of-dialog","slug":"towards-automatic-evaluation-of-dialog","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","date":"2021-02-20","arxiv_id":"2102.10242","repositories_listed":1,"syntology":null},{"url":"/paper/deep-latent-competition-learning-to-race","slug":"deep-latent-competition-learning-to-race","title":"Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space","date":"2021-02-19","arxiv_id":"2102.09812","repositories_listed":1,"syntology":null},{"url":"/paper/sim-env-decoupling-openai-gym-environments","slug":"sim-env-decoupling-openai-gym-environments","title":"Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models","date":"2021-02-19","arxiv_id":"2102.09824","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-doubly-constrained-batch","slug":"continuous-doubly-constrained-batch","title":"Continuous Doubly Constrained Batch Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09225","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/continuous-doubly-constrained-batch#ran","syntology_url":"https://syntology.ai/paper/2102.09225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09225"}},"official":{"repos":["amazon-research/cdc-batch-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-reinforcement-learning-of-3d","slug":"multi-agent-reinforcement-learning-of-3d","title":"Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes","date":"2021-02-18","arxiv_id":"2102.09137","repositories_listed":1,"syntology":null},{"url":"/paper/seapearl-a-constraint-programming-solver","slug":"seapearl-a-constraint-programming-solver","title":"SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09193","repositories_listed":1,"syntology":null},{"url":"/paper/developing-parsimonious-ensembles-using-1","slug":"developing-parsimonious-ensembles-using-1","title":"Developing parsimonious ensembles using predictor diversity within a reinforcement learning framework","date":"2021-02-15","arxiv_id":"2102.07344","repositories_listed":1,"syntology":null},{"url":"/paper/does-standard-backpropagation-forget-less","slug":"does-standard-backpropagation-forget-less","title":"Does the Adam Optimizer Exacerbate Catastrophic Forgetting?","date":"2021-02-15","arxiv_id":"2102.07686","repositories_listed":1,"syntology":null},{"url":"/paper/how-rl-agents-behave-when-their-actions-are","slug":"how-rl-agents-behave-when-their-actions-are","title":"How RL Agents Behave When Their Actions Are Modified","date":"2021-02-15","arxiv_id":"2102.07716","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-electric-vehicle-charging","slug":"intelligent-electric-vehicle-charging","title":"Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning","date":"2021-02-15","arxiv_id":"2102.07359","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-multi-agent-reinforcement-learning","slug":"scaling-multi-agent-reinforcement-learning","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","date":"2021-02-15","arxiv_id":"2102.07475","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/scaling-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2102.07475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07475"}},"official":{"repos":["uoe-agents/seps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scrofazero-mastering-trick-taking-poker-game","slug":"scrofazero-mastering-trick-taking-poker-game","title":"ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning","date":"2021-02-15","arxiv_id":"2102.07495","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-learning-from-activity","slug":"interactive-learning-from-activity","title":"Interactive Learning from Activity Description","date":"2021-02-13","arxiv_id":"2102.07024","repositories_listed":1,"syntology":null},{"url":"/paper/ltl2action-generalizing-ltl-instructions-for","slug":"ltl2action-generalizing-ltl-instructions-for","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","date":"2021-02-13","arxiv_id":"2102.06858","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/ltl2action-generalizing-ltl-instructions-for#ran","syntology_url":"https://syntology.ai/paper/2102.06858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06858"}},"official":{"repos":["LTL2Action/LTL2Action"],"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/q-value-weighted-regression-reinforcement-1","slug":"q-value-weighted-regression-reinforcement-1","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","date":"2021-02-12","arxiv_id":"2102.06782","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/q-value-weighted-regression-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2102.06782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06782"}},"official":null}},{"url":"/paper/domain-adaptation-in-reinforcement-learning","slug":"domain-adaptation-in-reinforcement-learning","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","date":"2021-02-10","arxiv_id":"2102.05714","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domain-adaptation-in-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2102.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05714"}},"official":{"repos":["KarlXing/LUSR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-augmentation-an-exploration-strategy","slug":"policy-augmentation-an-exploration-strategy","title":"Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms","date":"2021-02-10","arxiv_id":"2102.05249","repositories_listed":1,"syntology":null},{"url":"/paper/risk-averse-offline-reinforcement-learning-1","slug":"risk-averse-offline-reinforcement-learning-1","title":"Risk-Averse Offline Reinforcement Learning","date":"2021-02-10","arxiv_id":"2102.05371","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-time-model-based-reinforcement","slug":"continuous-time-model-based-reinforcement","title":"Continuous-Time Model-Based Reinforcement Learning","date":"2021-02-09","arxiv_id":"2102.04764","repositories_listed":1,"syntology":null},{"url":"/paper/learning-state-representations-from-random","slug":"learning-state-representations-from-random","title":"Learning State Representations from Random Deep Action-conditional Predictions","date":"2021-02-09","arxiv_id":"2102.04897","repositories_listed":1,"syntology":null},{"url":"/paper/reverb-a-framework-for-experience-replay","slug":"reverb-a-framework-for-experience-replay","title":"Reverb: A Framework For Experience Replay","date":"2021-02-09","arxiv_id":"2102.04736","repositories_listed":1,"syntology":null},{"url":"/paper/rl-reach-reproducible-reinforcement-learning","slug":"rl-reach-reproducible-reinforcement-learning","title":"rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks","date":"2021-02-09","arxiv_id":"2102.04916","repositories_listed":1,"syntology":null},{"url":"/paper/grid-to-graph-flexible-spatial-relational","slug":"grid-to-graph-flexible-spatial-relational","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","date":"2021-02-08","arxiv_id":"2102.04220","repositories_listed":1,"syntology":null},{"url":"/paper/rl-scope-cross-stack-profiling-for-deep","slug":"rl-scope-cross-stack-profiling-for-deep","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","date":"2021-02-08","arxiv_id":"2102.04285","repositories_listed":1,"syntology":null},{"url":"/paper/sparsely-ensembled-convolutional-neural","slug":"sparsely-ensembled-convolutional-neural","title":"Sparsely ensembled convolutional neural network classifiers via reinforcement learning","date":"2021-02-07","arxiv_id":"2102.03921","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-reinforcement-learning-for","slug":"explainable-reinforcement-learning-for","title":"Explainable Reinforcement Learning for Longitudinal Control","date":"2021-02-06","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"93e3fa3330f746b0ebd419d8eb42cc914b4d38ed8bae341b5b3009ef1930abb3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}