{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125},{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99},{"id":"2011.01387","title":"Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition","created":"2020-11-02","cited_by_count":96},{"id":"2105.08328","title":"Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning","created":"2021-05-18","cited_by_count":92},{"id":"2103.00073","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","created":"2021-02-26","cited_by_count":86},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64},{"id":"1907.03613","title":"Data Efficient Reinforcement Learning for Legged Robots","created":"2019-07-08","cited_by_count":63},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63},{"id":"2404.05695","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","created":"2024-04-08","cited_by_count":53},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47},{"id":"2103.09499","title":"Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs","created":"2021-03-17","cited_by_count":30},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27},{"id":"2011.04741","title":"Learning Task Space Actions for Bipedal Locomotion","created":"2020-11-09","cited_by_count":21},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19},{"id":"2311.02847","title":"Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs","created":"2023-11-06","cited_by_count":19},{"id":"2203.07589","title":"Sim-to-Real Learning of Footstep-Constrained Bipedal Dynamic Walking","created":"2022-03-15","cited_by_count":13},{"id":"2108.13619","title":"A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures","created":"2021-08-31","cited_by_count":12},{"id":"2110.00541","title":"Validating Robotics Simulators on Real-World Impacts","created":"2021-10-01","cited_by_count":11},{"id":"2209.11082","title":"Bypassing the Simulation-to-reality Gap: Online Reinforcement Learning using a Supervisor","created":"2022-09-22","cited_by_count":6},{"id":"2309.16074","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","created":"2023-09-28","cited_by_count":5},{"id":"2203.15107","title":"Motion Planning for Agile Legged Locomotion using Failure Margin Constraints","created":"2022-03-28","cited_by_count":1}],"next_cursor":null}