{"total":11,"rows":[{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2206.08442","title":"A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2203.12048","title":"Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2311.17855","title":"Maximum Entropy Model Correction in Reinforcement Learning","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2410.07096","title":"Rejecting Hallucinated State Targets during Planning","created":"2024-10-09","cited_by_count":1,"area":null}],"next_cursor":null}