{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76},{"id":"2407.10353","title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","created":"2024-07-14","cited_by_count":75},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62},{"id":"2406.06005","title":"WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts","created":"2024-06-10","cited_by_count":61},{"id":"2501.02116","title":"Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning","created":"2025-01-03","cited_by_count":61},{"id":"2010.03110","title":"Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning","created":"2020-10-07","cited_by_count":53},{"id":"1908.05224","title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","created":"2019-08-13","cited_by_count":42},{"id":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40},{"id":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","cited_by_count":39},{"id":"2409.20514","title":"Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation","created":"2024-09-30","cited_by_count":39},{"id":"2103.00946","title":"A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulation","created":"2021-03-01","cited_by_count":38},{"id":"2208.01160","title":"Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot","created":"2022-08-01","cited_by_count":38},{"id":"1812.10576","title":"Deconfounding Reinforcement Learning in Observational Settings","created":"2018-12-26","cited_by_count":36},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","cited_by_count":27},{"id":"2308.16820","title":"Learning Whole-body Manipulation for Quadrupedal Robot","created":"2023-08-31","cited_by_count":25},{"id":"2002.02836","title":"Causally Correct Partial Models for Reinforcement Learning","created":"2020-02-07","cited_by_count":24},{"id":"2406.01152","title":"Learning-based legged locomotion; state of the art and future perspectives","created":"2024-06-03","cited_by_count":23},{"id":"2403.20328","title":"Learning Visual Quadrupedal Loco-Manipulation from Demonstrations","created":"2024-03-29","cited_by_count":20},{"id":"2103.08107","title":"Mutual Information State Intrinsic Control","created":"2021-03-15","cited_by_count":18},{"id":"2011.08811","title":"Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs","created":"2020-11-17","cited_by_count":16},{"id":"2409.04882","title":"Learning to Open and Traverse Doors with a Legged Manipulator","created":"2024-09-07","cited_by_count":16},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12},{"id":"2212.08954","title":"Cascaded Compositional Residual Learning for Complex Interactive Behaviors","created":"2022-12-17","cited_by_count":10},{"id":"2307.00383","title":"Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration","created":"2023-07-01","cited_by_count":10},{"id":"2403.18197","title":"LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators","created":"2024-03-27","cited_by_count":10},{"id":"2312.11091","title":"Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling","created":"2023-12-18","cited_by_count":8},{"id":"2406.14655","title":"HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation","created":"2024-06-20","cited_by_count":7},{"id":"2311.00112","title":"Hierarchical Optimization-based Control for Whole-body Loco-manipulation of Heavy Objects","created":"2023-10-31","cited_by_count":6},{"id":"2210.03442","title":"Contact Optimization for Non-Prehensile Loco-Manipulation via Hierarchical Model Predictive Control","created":"2022-10-07","cited_by_count":5},{"id":"2209.08662","title":"Multi-contact MPC for Dynamic Loco-manipulation on Humanoid Robots","created":"2022-09-18","cited_by_count":4},{"id":"2403.14300","title":"DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision","created":"2024-03-21","cited_by_count":3},{"id":"2303.09628","title":"Efficient Learning of High Level Plans from Play","created":"2023-03-16","cited_by_count":2},{"id":"2410.08065","title":"Dynamic Object Catching with Quadruped Robot Front Legs","created":"2024-10-10","cited_by_count":2}],"next_cursor":null}