{"total":50,"rows":[{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2502.19009","title":"Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning","created":"2025-02-26","cited_by_count":13,"area":"deeprl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2407.04522","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","created":"2024-07-05","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"id":"2504.06048","title":"Trust-Region Twisted Policy Improvement","created":"2025-04-08","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2405.11740","title":"Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2406.15025","title":"SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning","created":"2024-06-21","cited_by_count":3,"area":"deeprl"},{"id":"2505.24784","title":"AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models","created":"2025-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.18482","title":"Reliability-Adjusted Prioritized Experience Replay","created":"2025-06-23","cited_by_count":3,"area":"deeprl"},{"id":"2407.20651","title":"Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations","created":"2024-07-30","cited_by_count":2,"area":"deeprl"},{"id":"2502.16634","title":"OptionZero: Planning with Learned Options","created":"2025-02-23","cited_by_count":2,"area":"deeprl"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2507.06326","title":"Sample-Efficient Reinforcement Learning Controller for Deep Brain Stimulation in Parkinson's Disease","created":"2025-07-08","cited_by_count":2,"area":"deeprl"},{"id":"2509.01793","title":"STORI: A Benchmark and Taxonomy for Stochastic Environments","created":"2025-09-01","cited_by_count":2,"area":"deeprl"},{"id":"2511.09219","title":"Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization","created":"2025-11-12","cited_by_count":2,"area":"deeprl"},{"id":"2404.00651","title":"Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration","created":"2024-03-31","cited_by_count":1,"area":"deeprl"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2509.11233","title":"TransZero: Parallel Tree Expansion in MuZero using Transformer Networks","created":"2025-09-14","cited_by_count":1,"area":"deeprl"},{"id":"2601.21548","title":"Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2407.11044","title":"Generalizing soft actor-critic algorithms to discrete action spaces","created":"2024-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2410.01739","title":"Conceptual Belief-Informed Reinforcement Learning","created":"2024-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2410.03119","title":"Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems","created":"2024-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2501.09611","title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","created":"2025-01-16","cited_by_count":0,"area":"deeprl"},{"id":"2504.04164","title":"MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning","created":"2025-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2504.19625","title":"Rulebook: bringing co-routines to reinforcement learning environments","created":"2025-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2506.21771","title":"Gradient-Based Neuroplastic Adaptation for Concurrent Optimization of Neuro-Fuzzy Networks","created":"2025-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2509.04815","title":"An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning","created":"2025-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2510.06649","title":"Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2510.11736","title":"AI Agents for the Dhumbal Card Game: A Comparative Study","created":"2025-10-10","cited_by_count":0,"area":"deeprl"},{"id":"2510.22859","title":"Guardian: Decoupling Exploration from Safety in Reinforcement Learning","created":"2025-10-26","cited_by_count":0,"area":"deeprl"},{"id":"2603.01452","title":"Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning","created":"2026-03-02","cited_by_count":0,"area":"deeprl"},{"id":"2603.27751","title":"SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games","created":"2026-03-29","cited_by_count":0,"area":"deeprl"},{"id":"2607.00811","title":"From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training","created":"2026-07-01","cited_by_count":0,"area":"deeprl"},{"id":"2607.04153","title":"Mask-based Predictive Representations for Reinforcement Learning","created":"2026-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2607.07769","title":"Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.02801","title":"VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.14564","title":"Chunk-wise Model-based Policy Optimization","created":"2026-10-10","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}