{"total":58,"rows":[{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42,"area":"offlinerl"},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2110.13578","title":"Distributional Reinforcement Learning for Multi-Dimensional Reward Functions","created":"2021-10-26","cited_by_count":22,"area":null},{"id":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2105.04196","title":"AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning","created":"2021-05-10","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2312.11118","title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","created":"2023-12-18","cited_by_count":14,"area":null},{"id":"2210.11825","title":"Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents","created":"2022-10-21","cited_by_count":10,"area":null},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2212.14749","title":"Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communications","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2202.00769","title":"Distributional Reinforcement Learning with Regularized Wasserstein Loss","created":"2022-02-01","cited_by_count":8,"area":null},{"id":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2201.10003","title":"Reinforcement Learning Your Way: Agent Characterization through Policy Regularization","created":"2022-01-21","cited_by_count":6,"area":null},{"id":"2206.13901","title":"Value Function Decomposition for Iterative Design of Reinforcement Learning Agents","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2310.02360","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2109.10632","title":"Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning","created":"2021-09-22","cited_by_count":3,"area":null},{"id":"2204.06407","title":"Flexible Multiple-Objective Reinforcement Learning for Chip Placement","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2311.02215","title":"Towards model-free RL algorithms that scale well with unstructured data","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2506.16016","title":"Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations","created":"2025-06-19","cited_by_count":3,"area":"deeprl"},{"id":"2102.11995","title":"A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2103.08070","title":"Learning robust driving policies without online exploration","created":"2021-03-15","cited_by_count":2,"area":"driving"},{"id":"2106.15868","title":"Decomposing the Prediction Problem; Autonomous Navigation by neoRL Agents","created":"2021-06-30","cited_by_count":2,"area":null},{"id":"2201.05819","title":"Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2204.06608","title":"Modularity benefits reinforcement learning agents with competing homeostatic drives","created":"2022-04-13","cited_by_count":2,"area":null},{"id":"2405.11784","title":"Reward-Punishment Reinforcement Learning with Maximum Entropy","created":"2024-05-20","cited_by_count":2,"area":"deeprl"},{"id":"2408.07660","title":"Off-Policy Reinforcement Learning with High Dimensional Reward","created":"2024-08-14","cited_by_count":2,"area":"deeprl"},{"id":"2409.08724","title":"Quasimetric Value Functions with Dense Rewards","created":"2024-09-13","cited_by_count":2,"area":"deeprl"},{"id":"2505.02483","title":"Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2302.01471","title":"User-centric Heterogeneous-action Deep Reinforcement Learning for Virtual Reality in the Metaverse over Wireless Networks","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2405.03878","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","created":"2024-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2501.04068","title":"Explainable Reinforcement Learning for Formula One Race Strategy","created":"2025-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2501.05501","title":"Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning Agents","created":"2025-01-09","cited_by_count":1,"area":"safety"},{"id":"2605.06066","title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2110.02879","title":"Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2202.12622","title":"Towards neoRL networks; the emergence of purposive graphs","created":"2022-02-25","cited_by_count":0,"area":null},{"id":"2208.12627","title":"Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models","created":"2022-08-26","cited_by_count":0,"area":null},{"id":"2301.05300","title":"Deep Reinforcement Learning for Asset Allocation: Reward Clipping","created":"2023-01-02","cited_by_count":0,"area":null},{"id":"2303.04349","title":"Virtual Reality in Metaverse over Wireless Networks with User-centered Deep Reinforcement Learning","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2308.04083","title":"Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2405.08053","title":"Radio Resource Management and Path Planning in Intelligent Transportation Systems via Reinforcement Learning for Environmental Sustainability","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2411.14783","title":"Segmenting Action-Value Functions Over Time-Scales in SARSA via TD($\\Delta$)","created":"2024-11-22","cited_by_count":0,"area":"deeprl"},{"id":"2412.13851","title":"From approximation error to optimality gap -- Explaining the performance impact of opportunity cost approximation in integrated demand management and vehicle routing","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2503.13414","title":"Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2509.09852","title":"Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2603.20230","title":"Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving","created":"2026-03-06","cited_by_count":0,"area":"driving"},{"id":"2606.18537","title":"Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents","created":"2026-06-16","cited_by_count":0,"area":"offlinerl"},{"id":"2606.28152","title":"Regularized Reward-Punishment Reinforcement Learning","created":"2026-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2607.29559","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.09762","title":"Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition","created":"2026-08-10","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}