{"list":"other","total":63,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"1703.09327","title":"DART: Noise Injection for Robust Imitation Learning","created":"2017-03-27","cited_by_count":191},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"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":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"1406.5979","title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning","created":"2014-06-23","cited_by_count":118},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96},{"id":"1703.01030","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","created":"2017-03-03","cited_by_count":93},{"id":"2502.10325","title":"Process Reward Models for LLM Agents: Practical Framework and Directions","created":"2025-02-14","cited_by_count":85},{"id":"2407.15007","title":"Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning","created":"2024-07-20","cited_by_count":74},{"id":"1803.00606","title":"On Oracle-Efficient PAC RL with Rich Observations","created":"2018-03-01","cited_by_count":71},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"2006.12484","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","created":"2020-06-22","cited_by_count":66},{"id":"1610.03518","title":"Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model","created":"2016-10-11","cited_by_count":54},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51},{"id":"1502.02206","title":"Learning to Search Better Than Your Teacher","created":"2015-02-08","cited_by_count":50},{"id":"1401.3436","title":"Online Planning Algorithms for POMDPs","created":"2014-01-15","cited_by_count":45},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40},{"id":"2007.12173","title":"Bridging the Imitation Gap by Adaptive Insubordination","created":"2020-07-23","cited_by_count":38},{"id":"1711.06391","title":"Data-driven Planning via Imitation Learning","created":"2017-11-17","cited_by_count":36},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35},{"id":"2208.02225","title":"Sequence Model Imitation Learning with Unobserved Contexts","created":"2022-08-03","cited_by_count":34},{"id":"2307.14619","title":"Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior","created":"2023-07-27","cited_by_count":33},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30},{"id":"2010.07452","title":"Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes","created":"2020-10-15","cited_by_count":23},{"id":"2012.15566","title":"Robust Asymmetric Learning in POMDPs","created":"2020-12-31","cited_by_count":23},{"id":"2210.01841","title":"Learning Perception-Aware Agile Flight in Cluttered Environments","created":"2022-10-04","cited_by_count":23},{"id":"2304.05889","title":"Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL","created":"2023-04-12","cited_by_count":22},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21},{"id":"2211.01991","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","created":"2022-11-03","cited_by_count":18},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18},{"id":"2307.03186","title":"TGRL: An Algorithm for Teacher Guided Reinforcement Learning","created":"2023-07-06","cited_by_count":17},{"id":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16},{"id":"2210.14985","title":"Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing","created":"2022-10-26","cited_by_count":15},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14},{"id":"2412.00985","title":"Provable Partially Observable Reinforcement Learning with Privileged Information","created":"2024-12-01","cited_by_count":13},{"id":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","cited_by_count":13},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8},{"id":"2412.13662","title":"When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?","created":"2024-12-18","cited_by_count":7},{"id":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6},{"id":"2412.09149","title":"Student-Informed Teacher Training","created":"2024-12-12","cited_by_count":6},{"id":"2503.20839","title":"TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion","created":"2025-03-26","cited_by_count":5},{"id":"2502.08632","title":"Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning","created":"2025-02-12","cited_by_count":3},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3},{"id":"1804.02573","title":"Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering","created":"2018-04-07","cited_by_count":1}],"next_cursor":null}