{"total":75,"rows":[{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"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":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"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":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18,"area":"deeprl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2406.16121","title":"Diffusion Spectral Representation for Reinforcement Learning","created":"2024-06-23","cited_by_count":15,"area":"diffusion"},{"id":"2503.01206","title":"Action Tokenizer Matters in In-Context Imitation Learning","created":"2025-03-03","cited_by_count":14,"area":"offlinerl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2405.15384","title":"Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate","created":"2024-05-24","cited_by_count":10,"area":"deeprl"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2506.08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"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":"2602.12829","title":"FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching","created":"2026-02-13","cited_by_count":6,"area":"diffusion"},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"id":"2604.04539","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","created":"2026-04-06","cited_by_count":5,"area":"deeprl"},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2404.07465","title":"Offline Reinforcement Learning with Domain-Unlabeled Data","created":"2024-04-11","cited_by_count":3,"area":"offlinerl"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2409.19231","title":"Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning","created":"2024-09-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","cited_by_count":3,"area":"offlinerl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2602.08557","title":"Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation","created":"2026-02-09","cited_by_count":3,"area":"deeprl"},{"id":"2502.08004","title":"Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2506.17155","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","created":"2025-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2510.23216","title":"Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach","created":"2025-10-27","cited_by_count":2,"area":"deeprl"},{"id":"2511.11592","title":"Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2601.22044","title":"SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control","created":"2026-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2607.15003","title":"SMC-ES: Automated synthesis of formally verified control policies","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2510.12096","title":"Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning","created":"2025-10-14","cited_by_count":1,"area":"deeprl"},{"id":"2605.09364","title":"MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","created":"2026-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2605.20609","title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"id":"2402.05950","title":"SQT -- std $Q$-target","created":"2024-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2402.05951","title":"MinMaxMin $Q$-learning","created":"2024-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2403.05732","title":"Conservative DDPG -- Pessimistic RL without Ensemble","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2405.00877","title":"Markov flow policy -- deep MC","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.02572","title":"Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2407.01310","title":"Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces","created":"2024-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2501.03676","title":"SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks","created":"2025-01-07","cited_by_count":0,"area":"offlinerl"},{"id":"2504.21585","title":"Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning","created":"2025-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2509.19771","title":"Frictional Q-Learning","created":"2025-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2510.01457","title":"A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization","created":"2025-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2511.16090","title":"Mitigating Estimation Bias with Representation Learning in TD Error-Driven Regularization","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.00027","title":"Representation Learning Enhanced Deep Reinforcement Learning for Optimal Operation of Hydrogen-based Multi-Energy Systems","created":"2026-01-17","cited_by_count":0,"area":"deeprl"},{"id":"2603.02935","title":"Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2603.08588","title":"Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control","created":"2026-03-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.00787","title":"SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.14026","title":"R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.14174","title":"Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.05555","title":"Representation Learning Enables Scalable Multitask Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.21297","title":"NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.31291","title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.13498","title":"Factorized Spectral Representations for Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2607.19628","title":"HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2608.07086","title":"Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.20098","title":"CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning","created":"2026-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.34018","title":"Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}