{"total":69,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38,"area":null},{"id":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"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":"2205.14105","title":"Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2410.15474","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2205.14211","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2303.10227","title":"Conversational Tree Search: A New Hybrid Dialog Task","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2106.15380","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","created":"2021-06-29","cited_by_count":6,"area":null},{"id":"2112.04123","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2304.01547","title":"Regularization of the policy updates for stabilizing Mean Field Games","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2308.12772","title":"Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2402.07963","title":"SPO: Sequential Monte Carlo Policy Optimisation","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2406.02213","title":"Random Policy Evaluation Uncovers Policies of Generative Flow Networks","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2509.03030","title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","created":"2025-09-03","cited_by_count":4,"area":"deeprl"},{"id":"2310.19804","title":"A Kernel Perspective on Behavioural Metrics for Markov Decision Processes","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2406.03678","title":"Reflective Policy Optimization","created":"2024-06-06","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":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2105.09716","title":"A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2508.21443","title":"Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning","created":"2025-08-29","cited_by_count":2,"area":"deeprl"},{"id":"2107.07659","title":"Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2203.10445","title":"Smoothing Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2203.11677","title":"Robust Action Gap Increasing with Clipped Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2502.03854","title":"Mirror Descent Actor Critic via Bounded Advantage Learning","created":"2025-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2504.11118","title":"Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement Learning","created":"2025-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2506.18627","title":"Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2602.10894","title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2608.01223","title":"Perspectives on Tsallis Statistics for Artificial Intelligence","created":"2026-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2107.05798","title":"Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2109.09037","title":"Dual Behavior Regularized Reinforcement Learning","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2109.09038","title":"Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2112.15568","title":"Actor Loss of Soft Actor Critic Explained","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2204.04892","title":"JORLDY: a fully customizable open source framework for reinforcement learning","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2205.07467","title":"$q$-Munchausen Reinforcement Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2205.07885","title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2304.10860","title":"On the Importance of Exploration for Real Life Learned Algorithms","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2306.02766","title":"Networked Communication for Decentralised Agents in Mean-Field Games","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2405.02201","title":"Regularized Q-learning through Robust Averaging","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2408.11607","title":"Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2410.22752","title":"SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving","created":"2024-10-30","cited_by_count":0,"area":"driving"},{"id":"2503.00227","title":"The Learning Approach to Games","created":"2025-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2505.03323","title":"Unraveling the Rainbow: can value-based methods schedule?","created":"2025-05-06","cited_by_count":0,"area":"deeprl"},{"id":"2507.05465","title":"2048: Reinforcement Learning in a Delayed Reward Environment","created":"2025-07-07","cited_by_count":0,"area":"deeprl"},{"id":"2510.24432","title":"Fill in the Blanks: Accelerating Q-Learning with a Handful of Demonstrations in Sparse Reward Settings","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2602.04737","title":"Rationality Measurement and Theory for Reinforcement Learning Agents","created":"2026-02-04","cited_by_count":0,"area":"deeprl"},{"id":"2603.07833","title":"Gradient Iterated Temporal-Difference Learning","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2605.02320","title":"ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields","created":"2026-05-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}