{"list":"other","total":85,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"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":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139},{"id":"1506.05254","title":"Gradient Estimation Using Stochastic Computation Graphs","created":"2015-06-17","cited_by_count":121},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2010.02903","title":"Keep CALM and Explore: Language Models for Action Generation in Text-based Games","created":"2020-10-06","cited_by_count":108},{"id":"1606.04460","title":"Model-Free Episodic Control","created":"2016-06-14","cited_by_count":102},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92},{"id":"2410.15115","title":"On Designing Effective RL Reward at Training Time for LLM Reasoning","created":"2024-10-19","cited_by_count":87},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63},{"id":"1803.01840","title":"TACO: Learning Task Decomposition via Temporal Alignment for Control","created":"2018-03-02","cited_by_count":62},{"id":"2302.00763","title":"Collaborating with language models for embodied reasoning","created":"2023-02-01","cited_by_count":61},{"id":"2405.01534","title":"Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks","created":"2024-05-02","cited_by_count":52},{"id":"2107.07599","title":"Partially Observable Markov Decision Processes (POMDPs) and Robotics","created":"2021-07-15","cited_by_count":49},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"1905.01756","title":"P3O: Policy-on Policy-off Policy Optimization","created":"2019-05-05","cited_by_count":37},{"id":"2309.06687","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","created":"2023-09-13","cited_by_count":36},{"id":"2311.13373","title":"Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents","created":"2023-11-22","cited_by_count":30},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24},{"id":"1710.06574","title":"The Effects of Memory Replay in Reinforcement Learning","created":"2017-10-18","cited_by_count":23},{"id":"2002.02286","title":"EgoMap: Projective mapping and structured egocentric memory for Deep RL","created":"2020-01-24","cited_by_count":23},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22},{"id":"2411.09022","title":"DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models","created":"2024-11-13","cited_by_count":19},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17},{"id":"2312.09056","title":"ReCoRe: Regularized Contrastive Representation Learning of World Model","created":"2023-12-14","cited_by_count":11},{"id":"2101.04178","title":"Action Priors for Large Action Spaces in Robotics","created":"2021-01-11","cited_by_count":10},{"id":"2502.15214","title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning","created":"2025-02-21","cited_by_count":10},{"id":"2410.02511","title":"Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration","created":"2024-10-03","cited_by_count":9},{"id":"2304.11063","title":"Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions","created":"2023-04-18","cited_by_count":8},{"id":"2405.15194","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","created":"2024-05-24","cited_by_count":8},{"id":"2406.05872","title":"STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models","created":"2024-06-09","cited_by_count":8},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7},{"id":"2304.12958","title":"A Closer Look at Reward Decomposition for High-Level Robotic Explanations","created":"2023-04-25","cited_by_count":7},{"id":"2412.11484","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","created":"2024-12-16","cited_by_count":6},{"id":"2506.02522","title":"Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making","created":"2025-06-03","cited_by_count":5},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4}],"next_cursor":null}