{"total":27,"rows":[{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27,"area":null},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","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":"2305.16569","title":"Accelerating Value Iteration with Anchoring","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2205.07015","title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments","created":"2022-05-14","cited_by_count":9,"area":null},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","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":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","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":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2202.02396","title":"A Temporal-Difference Approach to Policy Gradient Estimation","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2304.05073","title":"A Tale of Sampling and Estimation in Discounted Reinforcement Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2203.11656","title":"Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2203.00636","title":"Distributional Reinforcement Learning for Scheduling of Chemical Production Processes","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2210.13011","title":"On Many-Actions Policy Gradient","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2301.08442","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2201.00570","title":"3DPG: Distributed Deep Deterministic Policy Gradient Algorithms for Networked Multi-Agent Systems","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2212.14066","title":"On the Convergence of Discounted Policy Gradient Methods","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2311.07315","title":"An introduction to reinforcement learning for neuroscience","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2403.07932","title":"Feint Behaviors and Strategies: Formalization, Implementation and Evaluation","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2504.03328","title":"Policy Optimization Algorithms in a Unified Framework","created":"2025-04-04","cited_by_count":0,"area":null}],"next_cursor":null}