{"list":"other","total":53,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"2212.03238","title":"Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior","created":"2022-12-06","cited_by_count":138},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2406.10759","title":"Humanoid Parkour Learning","created":"2024-06-15","cited_by_count":96},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2008.12775","title":"On the model-based stochastic value gradient for continuous reinforcement learning","created":"2020-08-28","cited_by_count":47},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47},{"id":"1912.11206","title":"Learning to Combat Compounding-Error in Model-Based Reinforcement Learning","created":"2019-12-24","cited_by_count":39},{"id":"2108.09779","title":"Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger","created":"2021-08-22","cited_by_count":38},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28},{"id":"1910.04142","title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models","created":"2019-10-09","cited_by_count":26},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20},{"id":"2504.16680","title":"Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots","created":"2025-04-23","cited_by_count":17},{"id":"2311.05818","title":"Learning Agile Bipedal Motions on a Quadrupedal Robot","created":"2023-11-10","cited_by_count":15},{"id":"2409.13678","title":"SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience","created":"2024-09-20","cited_by_count":14},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12},{"id":"1904.06786","title":"Curious iLQR: Resolving Uncertainty in Model-based RL","created":"2019-04-15","cited_by_count":11},{"id":"2410.08650","title":"Extended Friction Models for the Physics Simulation of Servo Actuators","created":"2024-10-11","cited_by_count":3},{"id":"2206.11884","title":"Augmenting differentiable physics with randomized smoothing","created":"2022-06-23","cited_by_count":2},{"id":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2},{"id":"2411.02189","title":"DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation","created":"2024-11-04","cited_by_count":2}],"next_cursor":null}