{"total":34,"rows":[{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2202.05780","title":"A Modern Self-Referential Weight Matrix That Learns to Modify Itself","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2205.12184","title":"Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2305.16569","title":"Accelerating Value Iteration with Anchoring","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2305.18161","title":"VA-learning as a more efficient alternative to Q-learning","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2205.15400","title":"Designing Rewards for Fast Learning","created":"2022-05-30","cited_by_count":7,"area":null},{"id":"2210.11317","title":"Dynamic selection of p-norm in linear adaptive filtering via online kernel-based reinforcement learning","created":"2022-10-20","cited_by_count":7,"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":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"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":"2309.07548","title":"Proximal Bellman mappings for reinforcement learning and their application to robust adaptive filtering","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2108.04462","title":"Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2312.12869","title":"Parameterized Projected Bellman Operator","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2110.03424","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2211.11620","title":"Simultaneously Updating All Persistence Values in Reinforcement Learning","created":"2022-11-21","cited_by_count":2,"area":null},{"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":"2105.03041","title":"Utilizing Skipped Frames in Action Repeats via Pseudo-Actions","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2205.03819","title":"Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods","created":"2022-05-08","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":"2207.07271","title":"Set-based value operators for non-stationary Markovian environments","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2208.03663","title":"Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning","created":"2022-08-07","cited_by_count":0,"area":null},{"id":"2210.11755","title":"online and lightweight kernel-based approximated policy iteration for dynamic p-norm linear adaptive filtering","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2605.11042","title":"Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.18782","title":"A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}