{"total":15,"rows":[{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"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":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2312.00279","title":"Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2106.01741","title":"Lifetime policy reuse and the importance of task capacity","created":"2021-06-03","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2608.06545","title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","created":"2026-08-06","cited_by_count":2,"area":null},{"id":"2104.06139","title":"Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2104.08543","title":"Planning with Expectation Models for Control","created":"2021-04-17","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":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2309.12841","title":"Reward Function Design for Crowd Simulation via Reinforcement Learning","created":"2023-09-22","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}],"next_cursor":null}