{"total":12,"rows":[{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118,"area":null},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36,"area":null},{"id":"2207.02442","title":"Transformers are Adaptable Task Planners","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2411.13410","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","created":"2024-11-20","cited_by_count":9,"area":null},{"id":"2212.02064","title":"E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2311.06673","title":"Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination","created":"2023-11-11","cited_by_count":6,"area":null},{"id":"2205.01853","title":"SMLT: A Serverless Framework for Scalable and Adaptive Machine Learning Design and Training","created":"2022-05-04","cited_by_count":4,"area":null},{"id":"2401.07553","title":"Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2106.01607","title":"Grounding Complex Navigational Instructions Using Scene Graphs","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2109.15147","title":"Reinforcement Learning with Information-Theoretic Actuation","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2202.03188","title":"Knowledge-Integrated Informed AI for National Security","created":"2022-02-04","cited_by_count":0,"area":null}],"next_cursor":null}