{"total":81,"rows":[{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40,"area":null},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2102.10264","title":"On Proximal Policy Optimization's Heavy-tailed Gradients","created":"2021-02-20","cited_by_count":31,"area":null},{"id":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27,"area":"moe"},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2405.00987","title":"S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic","created":"2024-05-02","cited_by_count":18,"area":"deeprl"},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2206.04115","title":"Simplifying Polylogarithms with Machine Learning","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2208.04055","title":"Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions","created":"2022-08-08","cited_by_count":14,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2105.14900","title":"A unified view of likelihood ratio and reparameterization gradients","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2101.09137","title":"Multi-hop RIS-Empowered Terahertz Communications: A DRL-based Hybrid Beamforming Design","created":"2021-01-22","cited_by_count":10,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2107.12216","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","created":"2021-07-26","cited_by_count":7,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2604.14054","title":"$\\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data","created":"2026-04-15","cited_by_count":7,"area":"distill"},{"id":"2606.25556","title":"BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2311.08290","title":"On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2106.08272","title":"Deep Reinforcement Learning for Conservation Decisions","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2102.12194","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2206.06827","title":"Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2104.05902","title":"Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2110.01833","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3,"area":null},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","cited_by_count":2,"area":null},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2402.12034","title":"When Do Off-Policy and On-Policy Policy Gradient Methods Align?","created":"2024-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2404.17687","title":"Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review","created":"2024-04-26","cited_by_count":2,"area":"deeprl"},{"id":"2503.05696","title":"A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation","created":"2025-03-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.11862","title":"Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning","created":"2025-05-17","cited_by_count":2,"area":"deeprl"},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2609.36939","title":"SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents","created":"2026-09-29","cited_by_count":2,"area":"agents"},{"id":"2103.14256","title":"Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2107.04987","title":"Coordinate-wise Control Variates for Deep Policy Gradients","created":"2021-07-11","cited_by_count":1,"area":null},{"id":"2201.09104","title":"Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning","created":"2022-01-22","cited_by_count":1,"area":null},{"id":"2202.00076","title":"Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2206.13714","title":"Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse","created":"2022-06-28","cited_by_count":1,"area":null},{"id":"2208.13125","title":"Normality-Guided Distributional Reinforcement Learning for Continuous Control","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2209.01054","title":"Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2210.13011","title":"On Many-Actions Policy Gradient","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2212.05237","title":"Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2302.00533","title":"Distillation Policy Optimization","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2403.04453","title":"Efficient Off-Policy Learning for High-Dimensional Action Spaces","created":"2024-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2202.02693","title":"Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2206.08499","title":"A Parametric Class of Approximate Gradient Updates for Policy Optimization","created":"2022-06-17","cited_by_count":0,"area":null},{"id":"2208.10583","title":"Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2311.18684","title":"Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning","created":"2023-11-30","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":"2405.20180","title":"Transformers and Slot Encoding for Sample Efficient Physical World Modelling","created":"2024-05-30","cited_by_count":0,"area":"wm"},{"id":"2407.00744","title":"Disentangled Representations for Causal Cognition","created":"2024-06-30","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":"2505.11893","title":"RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving","created":"2025-05-17","cited_by_count":0,"area":"lr"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2511.07288","title":"Enabling Off-Policy Imitation Learning with Deep Actor Critic Stabilization","created":"2025-11-10","cited_by_count":0,"area":"offlinerl"},{"id":"2511.08241","title":"PrefPoE: Advantage-Guided Preference Fusion for Learning Where to Explore","created":"2025-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2604.17744","title":"Input-Side Variance Suppression under Non-Normal Transient Amplification in Continuous-Control Reinforcement Learning","created":"2026-04-20","cited_by_count":0,"area":"deeprl"},{"id":"2606.12251","title":"Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2607.25268","title":"Structure-aware Relative Policy Optimization for Ranking","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.26481","title":"Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.24174","title":"CREDO: Variance-Guided Rubric Evolution for Replay-Corrected Credit Assignment","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.36058","title":"ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.01399","title":"Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02505","title":"Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.04766","title":"Variance-Optimal Control Variates for Learning with Black-box Feedback","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}