{"list":"other","total":52,"rows":[{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2504.02792","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","created":"2025-04-03","cited_by_count":240},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2305.14909","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","created":"2023-05-24","cited_by_count":207},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"1507.04888","title":"Maximum Entropy Deep Inverse Reinforcement Learning","created":"2015-07-17","cited_by_count":176},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101},{"id":"2311.10227","title":"Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities","created":"2023-11-16","cited_by_count":89},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2006.07532","title":"Online Bayesian Goal Inference for Boundedly-Rational Planning Agents","created":"2020-06-13","cited_by_count":68},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59},{"id":"2011.09999","title":"Inverse Constrained Reinforcement Learning","created":"2020-11-19","cited_by_count":46},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43},{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43},{"id":"1906.02330","title":"Finding Friend and Foe in Multi-Agent Games","created":"2019-06-05","cited_by_count":42},{"id":"2305.16744","title":"Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought","created":"2023-05-26","cited_by_count":39},{"id":"2312.08566","title":"Learning adaptive planning representations with natural language guidance","created":"2023-12-13","cited_by_count":36},{"id":"1901.06085","title":"Theory of Minds: Understanding Behavior in Groups Through Inverse Planning","created":"2019-01-18","cited_by_count":30},{"id":"2502.11881","title":"Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models","created":"2025-02-17","cited_by_count":29},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28},{"id":"2502.15676","title":"AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling","created":"2025-02-21","cited_by_count":23},{"id":"2103.01933","title":"PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception","created":"2021-03-02","cited_by_count":22},{"id":"2407.06004","title":"Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models","created":"2024-07-08","cited_by_count":22},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19},{"id":"1308.4828","title":"The Sample-Complexity of General Reinforcement Learning","created":"2013-08-22","cited_by_count":18},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16},{"id":"2406.11911","title":"A Notion of Complexity for Theory of Mind via Discrete World Models","created":"2024-06-16","cited_by_count":16},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14},{"id":"1401.3455","title":"Monte Carlo Sampling Methods for Approximating Interactive POMDPs","created":"2014-01-15","cited_by_count":12},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11},{"id":"1611.08944","title":"Nonparametric General Reinforcement Learning","created":"2016-11-28","cited_by_count":10},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10},{"id":"2409.18073","title":"Infer Human's Intentions Before Following Natural Language Instructions","created":"2024-09-26","cited_by_count":10},{"id":"1903.01021","title":"A Strongly Asymptotically Optimal Agent in General Environments","created":"2019-03-04","cited_by_count":9},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9},{"id":"2403.00810","title":"Bootstrapping Cognitive Agents with a Large Language Model","created":"2024-02-25","cited_by_count":9},{"id":"2308.11071","title":"Neural Amortized Inference for Nested Multi-agent Reasoning","created":"2023-08-21","cited_by_count":8},{"id":"1812.01569","title":"Nested Reasoning About Autonomous Agents Using Probabilistic Programs","created":"2018-12-04","cited_by_count":7},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7},{"id":"2103.12694","title":"Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks","created":"2021-03-23","cited_by_count":6},{"id":"2409.10849","title":"Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind","created":"2024-09-17","cited_by_count":6},{"id":"2112.13404","title":"Abstractions of General Reinforcement Learning","created":"2021-12-26","cited_by_count":5},{"id":"2403.06854","title":"Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification","created":"2024-03-11","cited_by_count":4},{"id":"2406.08455","title":"AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind","created":"2024-06-12","cited_by_count":4},{"id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","created":"2025-08-21","cited_by_count":1}],"next_cursor":null}