{"total":8,"rows":[{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2309.00711","title":"Learning Shared Safety Constraints from Multi-task Demonstrations","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2510.15464","title":"Learning to Answer from Correct Demonstrations","created":"2025-10-17","cited_by_count":7,"area":null},{"id":"2308.06137","title":"A Game-Theoretic Framework for Joint Forecasting and Planning","created":"2023-08-11","cited_by_count":5,"area":null},{"id":"2310.13258","title":"ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2501.15618","title":"Your Learned Constraint is Secretly a Backward Reachable Tube","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2502.14160","title":"Efficient Inverse Multiagent Learning","created":"2025-02-20","cited_by_count":3,"area":null}],"next_cursor":null}