{"total":67,"rows":[{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035,"area":"agents"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299,"area":null},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165,"area":null},{"id":"2402.14034","title":"AgentScope: A Flexible yet Robust Multi-Agent Platform","created":"2024-02-21","cited_by_count":121,"area":"agents"},{"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":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117,"area":null},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2211.11736","title":"Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models","created":"2022-11-21","cited_by_count":58,"area":"mllm"},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55,"area":"lr"},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41,"area":"alignment"},{"id":"2208.02918","title":"LATTE: LAnguage Trajectory TransformEr","created":"2022-08-04","cited_by_count":40,"area":null},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2111.03205","title":"LILA: Language-Informed Latent Actions","created":"2021-11-05","cited_by_count":27,"area":null},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2008.06924","title":"Inverse Reinforcement Learning with Natural Language Goals","created":"2020-08-16","cited_by_count":20,"area":"offlinerl"},{"id":"2209.11972","title":"Ground then Navigate: Language-guided Navigation in Dynamic Scenes","created":"2022-09-24","cited_by_count":20,"area":null},{"id":"2203.13411","title":"Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers","created":"2022-03-25","cited_by_count":17,"area":null},{"id":"2306.16207","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","created":"2023-06-28","cited_by_count":17,"area":"agents"},{"id":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","cited_by_count":13,"area":"offlinerl"},{"id":"1905.09710","title":"Inverse Reinforcement Learning in Contextual MDPs","created":"2019-05-23","cited_by_count":12,"area":"offlinerl"},{"id":"2110.08258","title":"A Framework for Learning to Request Rich and Contextually Useful Information from Humans","created":"2021-10-14","cited_by_count":12,"area":null},{"id":"2109.09968","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","created":"2021-09-21","cited_by_count":11,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2402.14304","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2306.12554","title":"Improving Long-Horizon Imitation Through Instruction Prediction","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2204.05091","title":"Linguistic communication as (inverse) reward design","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2412.10917","title":"Adaptive Reward Design for Reinforcement Learning","created":"2024-12-14","cited_by_count":6,"area":"deeprl"},{"id":"2510.05865","title":"The Safety Challenge of World Models for Embodied AI Agents: A Review","created":"2025-10-07","cited_by_count":6,"area":"wm"},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2002.00412","title":"Combating False Negatives in Adversarial Imitation Learning","created":"2020-02-02","cited_by_count":4,"area":"offlinerl"},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2511.14565","title":"Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language","created":"2025-11-18","cited_by_count":4,"area":"alignment"},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2110.00842","title":"Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning","created":"2021-10-02","cited_by_count":2,"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":"2509.23155","title":"LaGEA: Language Guided Embodied Agents for Robotic Manipulation","created":"2025-09-27","cited_by_count":2,"area":"agents"},{"id":"2603.16978","title":"Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models","created":"2026-03-17","cited_by_count":2,"area":"alignment"},{"id":"2208.08374","title":"A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2309.11753","title":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.11614","title":"Learning a Hierarchical Planner from Humans in Multiple Generations","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2412.06877","title":"The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2501.15270","title":"Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning","created":"2025-01-25","cited_by_count":1,"area":"alignment"},{"id":"2509.23135","title":"Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm","created":"2025-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2510.19562","title":"DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2602.14844","title":"Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment","created":"2026-02-16","cited_by_count":1,"area":"offlinerl"},{"id":"2211.01724","title":"Learning Control by Iterative Inversion","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2409.16024","title":"From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2504.13241","title":"Recursive Deep Inverse Reinforcement Learning","created":"2025-04-17","cited_by_count":0,"area":"offlinerl"},{"id":"2511.19885","title":"Complex Instruction Following with Diverse Style Policies in Football Games","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2608.08273","title":"Action- and Language-Conditioned Video Assessment for Embodied Control","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.38955","title":"Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching","created":"2026-09-30","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}