{"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/papers/87","list_of":"/task/reinforcement-learning","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":87,"pages_in_order":132,"rows_per_page":100,"rows":[8601,8700],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"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","prev":"/task/reinforcement-learning/papers/86","next":"/task/reinforcement-learning/papers/88","papers":[{"url":null,"slug":"risk-aware-and-multi-objective-decision","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","date":"2021-02-01","arxiv_id":"2102.00966","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-rates-for-the-regret-of-offline","title":"Fast Rates for the Regret of Offline Reinforcement Learning","date":"2021-01-31","arxiv_id":"2102.00479","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-aided-monte-carlo","title":"Deep Reinforcement Learning Aided Monte Carlo Tree Search for MIMO Detection","date":"2021-01-30","arxiv_id":"2102.00178","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-product","title":"Deep Reinforcement Learning-Based Product Recommender for Online Advertising","date":"2021-01-30","arxiv_id":"2102.00333","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-stability-of-random-matrix-product","title":"On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning","date":"2021-01-30","arxiv_id":"2102.00185","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-machine-learning-help-in-solving-cargo","title":"Reinforcement Learning for Freight Booking Control Problems","date":"2021-01-29","arxiv_id":"2102.00092","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-vs-model-free-adaptive-control","title":"Learning-based vs Model-free Adaptive Control of a MAV under Wind Gust","date":"2021-01-29","arxiv_id":"2101.12501","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-voltage-control-using-structure","title":"Scalable Voltage Control using Structure-Driven Hierarchical Deep Reinforcement Learning","date":"2021-01-29","arxiv_id":"2102.00077","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-trading-for-order-execution-with","title":"Universal Trading for Order Execution with Oracle Policy Distillation","date":"2021-01-28","arxiv_id":"2103.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-android-malware-detection-system","title":"Robust Android Malware Detection System against Adversarial Attacks using Q-Learning","date":"2021-01-27","arxiv_id":"2101.12031","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-reinforcement-learning-via","title":"Safe Multi-Agent Reinforcement Learning via Shielding","date":"2021-01-27","arxiv_id":"2101.11196","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-sequence-generation-with-multi-agent","title":"Fast Sequence Generation with Multi-Agent Reinforcement Learning","date":"2021-01-24","arxiv_id":"2101.09698","repositories_listed":0,"syntology":null},{"url":null,"slug":"gst-group-sparse-training-for-accelerating","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","date":"2021-01-24","arxiv_id":"2101.09650","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-selection-using-reinforcement","title":"Feature Selection Using Reinforcement Learning","date":"2021-01-23","arxiv_id":"2101.09460","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-exploration-for-sample-efficient","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","date":"2021-01-23","arxiv_id":"2101.09458","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-learning-and-optimization-techniques","title":"Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art","date":"2021-01-23","arxiv_id":"2101.09505","repositories_listed":0,"syntology":null},{"url":null,"slug":"collision-free-flocking-with-a-dynamic-squad","title":"Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning","date":"2021-01-20","arxiv_id":"2101.08074","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-optimizes","title":"Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination","date":"2021-01-19","arxiv_id":"2101.07399","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-assembly-generative-architecture-with","title":"Spatial Assembly: Generative Architecture With Reinforcement Learning, Self Play and Tree Search","date":"2021-01-19","arxiv_id":"2101.07579","repositories_listed":0,"syntology":null},{"url":"/paper/claster-clustering-with-reinforcement","slug":"claster-clustering-with-reinforcement","title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","date":"2021-01-18","arxiv_id":"2101.07042","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-and-competitive-biases-for-multi","title":"Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning","date":"2021-01-18","arxiv_id":"2101.06890","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-embedded-lqr","title":"Deep Reinforcement Learning with Embedded LQR Controllers","date":"2021-01-18","arxiv_id":"2101.07175","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-policies-are-reward-robust","title":"Regularized Policies are Reward Robust","date":"2021-01-18","arxiv_id":"2101.07012","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-safe-hierarchical-planning-framework-for","title":"A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning","date":"2021-01-17","arxiv_id":"2101.06778","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-based-reinforcement-learning-for","title":"Affordance-based Reinforcement Learning for Urban Driving","date":"2021-01-15","arxiv_id":"2101.05970","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-haptic-shared","title":"Deep Reinforcement Learning for Haptic Shared Control in Unknown Tasks","date":"2021-01-15","arxiv_id":"2101.06227","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-evaluation-of-supervision-signals","title":"Empirical Evaluation of Supervision Signals for Style Transfer Models","date":"2021-01-15","arxiv_id":"2101.06172","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-recommender-1","title":"Reinforcement learning based recommender systems: A survey","date":"2021-01-15","arxiv_id":"2101.06286","repositories_listed":0,"syntology":null},{"url":null,"slug":"robusta-robust-automl-for-feature-selection","title":"Robusta: Robust AutoML for Feature Selection via Reinforcement Learning","date":"2021-01-15","arxiv_id":"2101.05950","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-fast-adaptation-for-grid","title":"Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning","date":"2021-01-13","arxiv_id":"2101.05317","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-synthesis-of-steady-state","title":"Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning","date":"2021-01-12","arxiv_id":"2101.04422","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-representation-meta-reinforcement-1","title":"Linear Representation Meta-Reinforcement Learning for Instant Adaptation","date":"2021-01-12","arxiv_id":"2101.04750","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-interactive-bayesian-reinforcement","title":"Deep Interactive Bayesian Reinforcement Learning via Meta-Learning","date":"2021-01-11","arxiv_id":"2101.03864","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-order-problem-solving-through-neural","title":"First-Order Problem Solving through Neural MCTS based Reinforcement Learning","date":"2021-01-11","arxiv_id":"2101.04167","repositories_listed":0,"syntology":null},{"url":null,"slug":"independent-policy-gradient-methods-for-1","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","date":"2021-01-11","arxiv_id":"2101.04233","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-screening-for-recurrent-diseases-a","title":"Active Screening for Recurrent Diseases: A Reinforcement Learning Approach","date":"2021-01-07","arxiv_id":"2101.02766","repositories_listed":0,"syntology":null},{"url":null,"slug":"coachnet-an-adversarial-sampling-approach-for","title":"CoachNet: An Adversarial Sampling Approach for Reinforcement Learning","date":"2021-01-07","arxiv_id":"2101.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"coding-for-distributed-multi-agent","title":"Coding for Distributed Multi-Agent Reinforcement Learning","date":"2021-01-07","arxiv_id":"2101.02308","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-quantum","title":"Deep Reinforcement Learning with Quantum-inspired Experience Replay","date":"2021-01-06","arxiv_id":"2101.02034","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-meta-reinforcement-learning-based","title":"Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces","date":"2021-01-06","arxiv_id":"2101.01883","repositories_listed":0,"syntology":null},{"url":null,"slug":"derivative-free-policy-optimization-for-risk","title":"Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity","date":"2021-01-04","arxiv_id":"2101.01041","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-safe-reinforcement-learning-for","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","date":"2021-01-02","arxiv_id":"2101.00531","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-flexibility-design-1","title":"Reinforcement Learning for Flexibility Design Problems","date":"2021-01-02","arxiv_id":"2101.00355","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reduction-approach-to-constrained","title":"A Reduction Approach to Constrained Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-fuel-optimization-strategy-for","title":"A Robust Fuel Optimization Strategy For Hybrid Electric Vehicles: A Deep Reinforcement Learning Based Continuous Time Design Approach","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-reinforcement-learning-for","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","date":"2021-01-01","arxiv_id":"2101.00240","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-learning-rates-for-multi-agent","title":"Adaptive Learning Rates for Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-multi-model-fusion-learning-for","title":"Adaptive Multi-model Fusion Learning for Sparse-Reward Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-distribution-shift-in-online","title":"Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-extrapolation-error-in-deep","title":"Addressing Extrapolation Error in Deep Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-examination-of-preference-based","title":"An Examination of Preference-based Reinforcement Learning for Treatment Recommendation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-pareto-frontier-through","title":"Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aspect-based-sentiment-classification-via","title":"Aspect-based Sentiment Classification via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-driven-robotic-manipulation","title":"Attention-driven Robotic Manipulation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"average-reward-reinforcement-learning-with-1","title":"Average Reward Reinforcement Learning with Monotonic Policy Improvement","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-reinforcement-learning-through","title":"Batch Reinforcement Learning Through Continuation Method","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-multi-agent-deep-reinforcement","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bounded-myopic-adversaries-for-deep","title":"Bounded Myopic Adversaries for Deep Reinforcement Learning Agents","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"brac-going-deeper-with-behavior-regularized","title":"BRAC+: Going Deeper with Behavior Regularized Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-imitation-and-reinforcement","title":"Combining Imitation and Reinforcement Learning with Free Energy Principle","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-in-multi-agent-reinforcement","title":"Communication in Multi-Agent Reinforcement Learning: Intention Sharing","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compute-and-memory-efficient-reinforcement","title":"Compute- and Memory-Efficient Reinforcement Learning with Latent Experience Replay","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-reinforcement-learning-with","title":"Constrained Reinforcement Learning With Learned Constraints","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinated-multi-agent-exploration-using","title":"Coordinated Multi-Agent Exploration Using Shared Goals","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"daylight-assessing-generalization-skills-of","title":"Daylight: Assessing Generalization Skills of Deep Reinforcement Learning Agents","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adaptive","title":"Deep Reinforcement Learning With Adaptive Combined Critics","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-reinforcement-learning-for-2","title":"Distributional Reinforcement Learning for Risk-Sensitive Policies","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"error-controlled-actor-critic-method-to","title":"Error Controlled Actor-Critic Method to Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-reinforcement-learning-through","title":"Explainable Reinforcement Learning Through Goal-Based Explanations","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-pareto-front-optimization-for","title":"Explicit Pareto Front Optimization for Constrained Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-with-dynamic-map-graph-structured","title":"Explore with Dynamic Map: Graph Structured Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-transferability-of-perturbations-in","title":"Exploring Transferability of Perturbations in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"factored-action-spaces-in-deep-reinforcement","title":"Factored Action Spaces in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"factoredrl-leveraging-factored-graphs-for","title":"FactoredRL: Leveraging Factored Graphs for Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-offline-reinforcement-learning","title":"Fine-Tuning Offline Reinforcement Learning with Model-Based Policy Optimization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fsv-learning-to-factorize-soft-value-function","title":"FSV: Learning to Factorize Soft Value Function for Cooperative Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"genetic-soft-updates-for-policy-evolution-in","title":"Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-to-entities-for","title":"Grounding Language to Entities for Generalization in Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-learning-to-branch-via","title":"Improving Learning to Branch via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-policy-gradients-for-online","title":"Incremental Policy Gradients for Online Reinforcement Learning Control","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-meta-reinforcement-learning","title":"Interpretable Meta-Reinforcement Learning with Actor-Critic Method","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-reinforcement-learning-with-1","title":"Interpretable Reinforcement Learning With Neural Symbolic Logic","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsically-guided-exploration-in-meta","title":"Intrinsically Guided Exploration in Meta Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-representations-for-reinforcement","title":"Invariant Representations for Reinforcement Learning without Reconstruction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-transferable-scheduling-policy-for","title":"Learning a Transferable Scheduling Policy for Various Vehicle Routing Problems based on Graph-centric Representation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-demonstrations-with-energy","title":"Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-latent-landmarks-for-generalizable","title":"Learning Latent Landmarks for Generalizable Planning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-predictive-communication-by","title":"Learning Predictive Communication by Imagination in Networked System Control","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-observe-with-reinforcement","title":"Learning to Observe with Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-with-informed","title":"Meta-Reinforcement Learning With Informed Policy Regularization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-planning-and-learning-with","title":"Monte-Carlo Planning and Learning with Language Action Value Estimates","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-exploration-with-backward","title":"Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-information-bottleneck-in","title":"Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"peril-probabilistic-embeddings-for-hybrid","title":"PERIL: Probabilistic Embeddings for hybrid Meta-Reinforcement and Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-atari-with-capsule-networks-a","title":"Playing Atari with Capsule Networks: A systematic comparison of CNN and CapsNets-based agents.","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-marginalized-importance-sampling","title":"Practical Marginalized Importance Sampling with the Successor Representation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-rich-observation-reinforcement","title":"Provable Rich Observation Reinforcement Learning with Combinatorial Latent States","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"r-latte-attention-module-for-visual-control","title":"R-LAtte: Attention Module for Visual Control via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reconnaissance-for-reinforcement-learning","title":"RECONNAISSANCE FOR REINFORCEMENT LEARNING WITH SAFETY CONSTRAINTS","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regioned-episodic-reinforcement-learning","title":"Regioned Episodic Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"8c2647397dcecef4065901ff6dd2d367ef1b330dd3694ef8df2d03f057260f30","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}