{"list":"other","total":55,"rows":[{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1704.03012","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","created":"2017-04-10","cited_by_count":124},{"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":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"2301.12050","title":"Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling","created":"2023-01-28","cited_by_count":88},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86},{"id":"1610.05182","title":"Learning and Transfer of Modulated Locomotor Controllers","created":"2016-10-17","cited_by_count":59},{"id":"1905.13320","title":"Combating the Compounding-Error Problem with a Multi-step Model","created":"2019-05-30","cited_by_count":54},{"id":"1512.04202","title":"Preconditioned Stochastic Gradient Descent","created":"2015-12-14","cited_by_count":50},{"id":"1910.04450","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","created":"2019-10-10","cited_by_count":40},{"id":"2405.15383","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","created":"2024-05-24","cited_by_count":40},{"id":"2006.16712","title":"Model-based Reinforcement Learning: A Survey","created":"2020-06-30","cited_by_count":39},{"id":"2410.23156","title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","created":"2024-10-30","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":"2006.15085","title":"What can I do here? A Theory of Affordances in Reinforcement Learning","created":"2020-06-26","cited_by_count":35},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26},{"id":"2510.04542","title":"Code World Models for General Game Playing","created":"2025-10-06","cited_by_count":26},{"id":"1902.09996","title":"The Termination Critic","created":"2019-02-26","cited_by_count":24},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23},{"id":"1607.05077","title":"Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay","created":"2016-07-18","cited_by_count":22},{"id":"2403.10454","title":"Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness","created":"2024-03-15","cited_by_count":17},{"id":"2503.20124","title":"Synthesizing world models for bilevel planning","created":"2025-03-26","cited_by_count":14},{"id":"2108.03213","title":"Temporally Abstract Partial Models","created":"2021-08-06","cited_by_count":11},{"id":"2501.00296","title":"From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models","created":"2024-12-31","cited_by_count":11},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10},{"id":"2509.26255","title":"ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning","created":"2025-09-30","cited_by_count":9},{"id":"2109.09876","title":"Context-Specific Representation Abstraction for Deep Option Learning","created":"2021-09-20","cited_by_count":8},{"id":"2011.02565","title":"Diversity-Enriched Option-Critic","created":"2020-11-04","cited_by_count":7},{"id":"1812.01488","title":"Natural Option Critic","created":"2018-12-04","cited_by_count":6},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5},{"id":"2201.09653","title":"The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning","created":"2022-01-24","cited_by_count":2}],"next_cursor":null}