{"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/69","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":69,"pages_in_order":132,"rows_per_page":100,"rows":[6801,6900],"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/68","next":"/task/reinforcement-learning/papers/70","papers":[{"url":null,"slug":"autotuning-pid-control-using-actor-critic","title":"Autotuning PID control using Actor-Critic Deep Reinforcement Learning","date":"2022-11-29","arxiv_id":"2212.00013","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-energy-management-and-demand","title":"Distributed Energy Management and Demand Response in Smart Grids: A Multi-Agent Deep Reinforcement Learning Framework","date":"2022-11-29","arxiv_id":"2211.15858","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-14","title":"Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration","date":"2022-11-29","arxiv_id":"2211.16385","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-closed","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","date":"2022-11-29","arxiv_id":"2211.15956","repositories_listed":0,"syntology":null},{"url":null,"slug":"accerl-policy-acceleration-framework-for-deep","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15023","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-assessment-of-demonstration","title":"Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15542","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-deep-reinforcement-learning-using","title":"Causal Deep Reinforcement Learning Using Observational Data","date":"2022-11-28","arxiv_id":"2211.15355","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-episodic-control","title":"Continuous Episodic Control","date":"2022-11-28","arxiv_id":"2211.15183","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypernetworks-for-zero-shot-transfer-in","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15457","repositories_listed":0,"syntology":null},{"url":null,"slug":"inapplicable-actions-learning-for-knowledge","title":"Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15589","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-good-trajectories-in-offline","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15612","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-aware-proximal-pessimistic-algorithms","title":"State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15065","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-generalization-for-robust-model-based","title":"Domain Generalization for Robust Model-Based Offline Reinforcement Learning","date":"2022-11-27","arxiv_id":"2211.14827","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-note-on-model-free-reinforcement-learning","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","date":"2022-11-25","arxiv_id":"2211.14250","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-improving-proactive-dialog-agents","title":"Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning","date":"2022-11-25","arxiv_id":"2211.15359","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-simulation-software-demonstration-for","title":"Software Simulation and Visualization of Quantum Multi-Drone Reinforcement Learning","date":"2022-11-24","arxiv_id":"2211.15375","repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-tree-search-algorithms-for-risk","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","date":"2022-11-23","arxiv_id":"2211.13032","repositories_listed":0,"syntology":null},{"url":null,"slug":"powderworld-a-platform-for-understanding","title":"Powderworld: A Platform for Understanding Generalization via Rich Task Distributions","date":"2022-11-23","arxiv_id":"2211.13051","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-agent-design-and","title":"Reinforcement Learning Agent Design and Optimization with Bandwidth Allocation Model","date":"2022-11-23","arxiv_id":"2211.12987","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-traffic-signal-1","title":"Reinforcement learning for traffic signal control in hybrid action space","date":"2022-11-23","arxiv_id":"2211.12956","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-continuous-action","title":"Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning","date":"2022-11-23","arxiv_id":"2211.13257","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-to-5","title":"A Deep Reinforcement Learning Approach to Rare Event Estimation","date":"2022-11-22","arxiv_id":"2211.12470","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-optimize","title":"A Reinforcement Learning Approach to Optimize Available Network Bandwidth Utilization","date":"2022-11-22","arxiv_id":"2211.11949","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-multimodal-interactive-agents-with","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","date":"2022-11-21","arxiv_id":"2211.11602","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cooperative-oversubscription-for","title":"Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11759","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-trajectory-stitching-for-improved","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11603","repositories_listed":0,"syntology":null},{"url":null,"slug":"physq-a-physics-informed-reinforcement","title":"PhysQ: A Physics Informed Reinforcement Learning Framework for Building Control","date":"2022-11-21","arxiv_id":"2211.11830","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneously-updating-all-persistence","title":"Simultaneously Updating All Persistence Values in Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11620","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-using-data-driven","title":"Safe Reinforcement Learning using Data-Driven Predictive Control","date":"2022-11-20","arxiv_id":"2211.11027","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-enhanced-deep-reinforcement","title":"Structure-Enhanced Deep Reinforcement Learning for Optimal Transmission Scheduling","date":"2022-11-20","arxiv_id":"2211.10827","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-perceived-safety-of-urban-city","title":"Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learning","date":"2022-11-19","arxiv_id":"2211.10660","repositories_listed":0,"syntology":null},{"url":null,"slug":"credit-cognisant-reinforcement-learning-for","title":"Credit-cognisant reinforcement learning for multi-agent cooperation","date":"2022-11-18","arxiv_id":"2211.10100","repositories_listed":0,"syntology":null},{"url":null,"slug":"alphasnake-policy-iteration-on-a","title":"AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process","date":"2022-11-17","arxiv_id":"2211.09622","repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-irregular-object-packing-via","title":"Planning Irregular Object Packing via Hierarchical Reinforcement Learning","date":"2022-11-17","arxiv_id":"2211.09382","repositories_listed":0,"syntology":null},{"url":null,"slug":"solar-power-driven-ev-charging-optimization","title":"Solar Power driven EV Charging Optimization with Deep Reinforcement Learning","date":"2022-11-17","arxiv_id":"2211.09479","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-pooling-reinforcement-learning-for","title":"Data-pooling Reinforcement Learning for Personalized Healthcare Intervention","date":"2022-11-16","arxiv_id":"2211.08998","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimum-information-divergence-of-q-functions","title":"Minimum information divergence of Q-functions for dynamic treatment resumes","date":"2022-11-16","arxiv_id":"2211.08741","repositories_listed":0,"syntology":null},{"url":null,"slug":"apt-adaptive-perceptual-quality-based-camera","title":"APT: Adaptive Perceptual quality based camera Tuning using reinforcement learning","date":"2022-11-15","arxiv_id":"2211.08504","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-transformer-for-offline-meta","title":"Contextual Transformer for Offline Meta Reinforcement Learning","date":"2022-11-15","arxiv_id":"2211.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-intelligence-requires-rethinking","title":"General Intelligence Requires Rethinking Exploration","date":"2022-11-15","arxiv_id":"2211.07819","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-adaptive","title":"Offline Reinforcement Learning with Adaptive Behavior Regularization","date":"2022-11-15","arxiv_id":"2211.08251","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-methods-for-wordle-a","title":"Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach","date":"2022-11-15","arxiv_id":"2211.10298","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-distributional-decision-based-black","title":"Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning","date":"2022-11-15","arxiv_id":"2211.08384","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-reinforcement-learning-with-ball","title":"Linear Reinforcement Learning with Ball Structure Action Space","date":"2022-11-14","arxiv_id":"2211.07419","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-automatic-history-matching-algorithm","title":"Parallel Automatic History Matching Algorithm Using Reinforcement Learning","date":"2022-11-14","arxiv_id":"2211.07434","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-are-contrastive-explanations-of","title":"(When) Are Contrastive Explanations of Reinforcement Learning Helpful?","date":"2022-11-14","arxiv_id":"2211.07719","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-conditioned-reinforcement-learning-in","title":"Goal-Conditioned Reinforcement Learning in the Presence of an Adversary","date":"2022-11-13","arxiv_id":"2211.06929","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-vector","title":"Deep Reinforcement Learning with Vector Quantized Encoding","date":"2022-11-12","arxiv_id":"2211.06733","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewards-encoding-environment-dynamics","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","date":"2022-11-12","arxiv_id":"2211.06527","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-commercial-cooling-systems-using","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","date":"2022-11-11","arxiv_id":"2211.07357","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergency-action-termination-for-immediate","title":"Emergency action termination for immediate reaction in hierarchical reinforcement learning","date":"2022-11-11","arxiv_id":"2211.06351","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-imitation-reinforcement-learning-for-1","title":"Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction","date":"2022-11-11","arxiv_id":"2211.06014","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-n-1-secure-hv-grid-flexibility","title":"Robust N-1 secure HV Grid Flexibility Estimation for TSO-DSO coordinated Congestion Management with Deep Reinforcement Learning","date":"2022-11-10","arxiv_id":"2211.05855","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-realizability-sufficient-for-off","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","date":"2022-11-10","arxiv_id":"2211.05311","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundation-models-for-semantic-novelty-in","title":"Foundation Models for Semantic Novelty in Reinforcement Learning","date":"2022-11-09","arxiv_id":"2211.04878","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-offline-data-in-online","title":"Leveraging Offline Data in Online Reinforcement Learning","date":"2022-11-09","arxiv_id":"2211.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-agent-to-multi-agent-in-deep","title":"Solving Collaborative Dec-POMDPs with Deep Reinforcement Learning Heuristics","date":"2022-11-09","arxiv_id":"2211.15411","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-in-deep-reinforcement-learning-a","title":"Pretraining in Deep Reinforcement Learning: A Survey","date":"2022-11-08","arxiv_id":"2211.03959","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-stepwise-fairness","title":"Reinforcement Learning with Stepwise Fairness Constraints","date":"2022-11-08","arxiv_id":"2211.03994","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-quantum-reinforcement-learning","title":"A Survey on Quantum Reinforcement Learning","date":"2022-11-07","arxiv_id":"2211.03464","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-predictive-clustering","title":"Reward-Predictive Clustering","date":"2022-11-07","arxiv_id":"2211.03281","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-federated-reinforcement","title":"Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control","date":"2022-11-04","arxiv_id":"2211.02296","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-reinforcement-learning-in","title":"A Survey on Reinforcement Learning in Aviation Applications","date":"2022-11-03","arxiv_id":"2211.02147","repositories_listed":0,"syntology":null},{"url":"/paper/lilgym-natural-language-visual-reasoning-with","slug":"lilgym-natural-language-visual-reasoning-with","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","date":"2022-11-03","arxiv_id":"2211.01994","repositories_listed":0,"syntology":null},{"url":null,"slug":"oracle-inequalities-for-model-selection-in","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","date":"2022-11-03","arxiv_id":"2211.02016","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-non-markovian","title":"Reinforcement Learning in Non-Markovian Environments","date":"2022-11-03","arxiv_id":"2211.01595","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-power-control","title":"Deep Reinforcement Learning for Power Control in Next-Generation WiFi Network Systems","date":"2022-11-02","arxiv_id":"2211.01107","repositories_listed":0,"syntology":null},{"url":"/paper/dual-generator-offline-reinforcement-learning","slug":"dual-generator-offline-reinforcement-learning","title":"Dual Generator Offline Reinforcement Learning","date":"2022-11-02","arxiv_id":"2211.01471","repositories_listed":0,"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/dual-generator-offline-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2211.01471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01471"}},"official":null}},{"url":null,"slug":"model-based-reinforcement-learning-with-a-1","title":"Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network","date":"2022-11-02","arxiv_id":"2211.00942","repositories_listed":0,"syntology":null},{"url":null,"slug":"wind-power-forecasting-considering-data","title":"Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach","date":"2022-11-02","arxiv_id":"2211.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-applied-to-trading","title":"Reinforcement Learning Applied to Trading Systems: A Survey","date":"2022-11-01","arxiv_id":"2212.06064","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-education-a-multi","title":"Reinforcement Learning in Education: A Multi-Armed Bandit Approach","date":"2022-11-01","arxiv_id":"2211.00779","repositories_listed":0,"syntology":null},{"url":null,"slug":"danzero-mastering-guandan-game-with","title":"DanZero: Mastering GuanDan Game with Reinforcement Learning","date":"2022-10-31","arxiv_id":"2210.17087","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacher-student-curriculum-learning-for","title":"Teacher-student curriculum learning for reinforcement learning","date":"2022-10-31","arxiv_id":"2210.17368","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-rate-distortion-theory-in-capacity-limited","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","date":"2022-10-30","arxiv_id":"2210.16877","repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-to-the-information-horizon-of-bamdps","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","date":"2022-10-30","arxiv_id":"2210.16872","repositories_listed":0,"syntology":null},{"url":null,"slug":"learninggroup-a-real-time-sparse-training-on","title":"LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning","date":"2022-10-29","arxiv_id":"2210.16624","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-contrastive-samples-for-identifying-and","title":"Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning","date":"2022-10-28","arxiv_id":"2210.17296","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-indoor-localization-via-reinforcement","title":"Hybrid Indoor Localization via Reinforcement Learning-based Information Fusion","date":"2022-10-27","arxiv_id":"2210.15132","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-using-model","title":"Meta-Reinforcement Learning Using Model Parameters","date":"2022-10-27","arxiv_id":"2210.15515","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-rl-sensing-aware-model-based","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","date":"2022-10-27","arxiv_id":"2210.15185","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-shape-demonstration-shaped-reinforcement","title":"D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning","date":"2022-10-26","arxiv_id":"2210.14428","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-guided-exploration-in-deep","title":"Knowledge-Guided Exploration in Deep Reinforcement Learning","date":"2022-10-26","arxiv_id":"2210.15670","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-deep-recurrent-reinforcement-learning","title":"Quantum deep recurrent reinforcement learning","date":"2022-10-26","arxiv_id":"2210.14876","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-based-meta-reinforcement-learning","title":"Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking","date":"2022-10-26","arxiv_id":"2210.14532","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-distributional-and-risk-sensitive","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","date":"2022-10-25","arxiv_id":"2210.14051","repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-divider-with-language-grounding-in","title":"Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning","date":"2022-10-25","arxiv_id":"2210.13942","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-explanation-for-reinforcement-learning","title":"Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance","date":"2022-10-24","arxiv_id":"2210.13507","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-reinforcement-learning-based-cnn","title":"Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing","date":"2022-10-24","arxiv_id":"2210.13464","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardness-in-markov-decision-processes-theory","title":"Hardness in Markov Decision Processes: Theory and Practice","date":"2022-10-24","arxiv_id":"2210.13075","repositories_listed":0,"syntology":null},{"url":null,"slug":"opportunistic-episodic-reinforcement-learning","title":"Opportunistic Episodic Reinforcement Learning","date":"2022-10-24","arxiv_id":"2210.13504","repositories_listed":0,"syntology":null},{"url":null,"slug":"oss-mentor-a-framework-for-improving","title":"OSS Mentor A framework for improving developers contributions via deep reinforcement learning","date":"2022-10-24","arxiv_id":"2210.13990","repositories_listed":0,"syntology":null},{"url":null,"slug":"reachability-aware-laplacian-representation","title":"Reachability-Aware Laplacian Representation in Reinforcement Learning","date":"2022-10-24","arxiv_id":"2210.13153","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-and-bandits-for-speech","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","date":"2022-10-24","arxiv_id":"2210.13623","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cooperative-reinforcement-learning","title":"A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal","date":"2022-10-23","arxiv_id":"2210.12841","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-predictive-coding-a-unified-neural","title":"Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning","date":"2022-10-23","arxiv_id":"2210.13461","repositories_listed":0,"syntology":null},{"url":null,"slug":"climate-change-policy-exploration-using","title":"Climate Change Policy Exploration using Reinforcement Learning","date":"2022-10-23","arxiv_id":"2211.17013","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-and-more-diverse-de-novo-molecular","title":"Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES","date":"2022-10-22","arxiv_id":"2210.12458","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-transfer-in-deep-reinforcement","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","date":"2022-10-22","arxiv_id":"2210.12448","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-reinforcement-learning-with-group","title":"Continual Vision-based Reinforcement Learning with Group Symmetries","date":"2022-10-21","arxiv_id":"2210.12301","repositories_listed":0,"syntology":null}],"record_sha256":"b275c6adeeb98a5d289d1fc176a2f39cddc4d94c562228aeb344cf1225cc1d77","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}