{"total":16,"rows":[{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2108.07555","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2205.05569","title":"Delayed Reinforcement Learning by Imitation","created":"2022-05-11","cited_by_count":16,"area":null},{"id":"2201.12403","title":"Planning and Learning with Adaptive Lookahead","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2305.07911","title":"Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2310.18919","title":"Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2404.05440","title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2205.13718","title":"Off-Beat Multi-Agent Reinforcement Learning","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2303.06654","title":"Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2305.16979","title":"Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2605.04345","title":"Structural Equivalence and Learning Dynamics in Delayed MARL","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2607.05077","title":"LangLoc: \"Tell Me What You See\"","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}