{"list":"other","total":88,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"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":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"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":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"1811.11214","title":"Understanding the impact of entropy on policy optimization","created":"2018-11-27","cited_by_count":176},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"1506.05254","title":"Gradient Estimation Using Stochastic Computation Graphs","created":"2015-06-17","cited_by_count":121},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"1611.01652","title":"A Differentiable Physics Engine for Deep Learning in Robotics","created":"2016-11-05","cited_by_count":108},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2104.03311","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","created":"2021-04-07","cited_by_count":103},{"id":"2104.02646","title":"gradSim: Differentiable simulation for system identification and visuomotor control","created":"2021-04-06","cited_by_count":100},{"id":"1502.02860","title":"Gaussian Processes for Data-Efficient Learning in Robotics and Control","created":"2015-02-10","cited_by_count":98},{"id":"1810.01054","title":"ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics","created":"2018-10-02","cited_by_count":98},{"id":"1902.05605","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","created":"2019-02-14","cited_by_count":95},{"id":"1703.02018","title":"Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation","created":"2017-03-06","cited_by_count":90},{"id":"1810.05762","title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","created":"2018-10-12","cited_by_count":90},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89},{"id":"1910.12807","title":"Better Exploration with Optimistic Actor-Critic","created":"2019-10-28","cited_by_count":88},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"2011.04217","title":"NeuralSim: Augmenting Differentiable Simulators with Neural Networks","created":"2020-11-09","cited_by_count":82},{"id":"2105.03655","title":"FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding","created":"2021-05-08","cited_by_count":81},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2007.02168","title":"Scalable Differentiable Physics for Learning and Control","created":"2020-07-04","cited_by_count":73},{"id":"2205.02909","title":"RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks","created":"2022-05-05","cited_by_count":72},{"id":"2106.05306","title":"DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact","created":"2021-06-09","cited_by_count":65},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2101.05917","title":"DiffPD: Differentiable Projective Dynamics","created":"2021-01-15","cited_by_count":62},{"id":"2105.10389","title":"Learning Visible Connectivity Dynamics for Cloth Smoothing","created":"2021-05-21","cited_by_count":62},{"id":"2304.14369","title":"Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics","created":"2023-04-27","cited_by_count":57},{"id":"1902.01240","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","created":"2019-02-04","cited_by_count":56},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55},{"id":"2305.17110","title":"IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality","created":"2023-05-26","cited_by_count":53},{"id":"2208.12250","title":"Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands","created":"2022-08-25","cited_by_count":51},{"id":"2008.12775","title":"On the model-based stochastic value gradient for continuous reinforcement learning","created":"2020-08-28","cited_by_count":47},{"id":"2407.10648","title":"Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics","created":"2024-07-15","cited_by_count":45},{"id":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","cited_by_count":40},{"id":"2109.07719","title":"Efficient Differentiable Simulation of Articulated Bodies","created":"2021-09-16","cited_by_count":39},{"id":"2205.01758","title":"Differentiable Simulation of Soft Multi-body Systems","created":"2022-05-03","cited_by_count":39},{"id":"2203.00663","title":"Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects","created":"2022-03-01","cited_by_count":37},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28},{"id":"2407.05560","title":"A Review of Differentiable Simulators","created":"2024-07-08","cited_by_count":28},{"id":"2203.00806","title":"Dojo: A Differentiable Physics Engine for Robotics","created":"2022-03-02","cited_by_count":26},{"id":"2403.08716","title":"DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation","created":"2024-03-13","cited_by_count":26},{"id":"2203.06856","title":"ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation","created":"2022-03-14","cited_by_count":24},{"id":"2207.00167","title":"Rethinking Optimization with Differentiable Simulation from a Global Perspective","created":"2022-06-28","cited_by_count":23},{"id":"2304.03223","title":"DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics","created":"2023-03-27","cited_by_count":23},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22},{"id":"2009.08973","title":"GRAC: Self-Guided and Self-Regularized Actor-Critic","created":"2020-09-18","cited_by_count":21},{"id":"2405.17784","title":"Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation","created":"2024-05-28","cited_by_count":20},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19},{"id":"2304.03274","title":"DiffMimic: Efficient Motion Mimicking with Differentiable Physics","created":"2023-04-06","cited_by_count":19},{"id":"2210.00664","title":"FRIDA: A Collaborative Robot Painter with a Differentiable, Real2Sim2Real Planning Environment","created":"2022-10-03","cited_by_count":18},{"id":"2205.02835","title":"Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics","created":"2022-05-05","cited_by_count":14},{"id":"2102.05791","title":"Differentiable Implicit Soft-Body Physics","created":"2021-02-11","cited_by_count":9},{"id":"2312.03297","title":"SoftMAC: Differentiable Soft Body Simulation with Forecast-based Contact Model and Two-way Coupling with Articulated Rigid Bodies and Clothes","created":"2023-12-06","cited_by_count":9},{"id":"2312.08710","title":"Gradient Informed Proximal Policy Optimization","created":"2023-12-14","cited_by_count":8},{"id":"2404.02887","title":"Learning Deployable Locomotion Control via Differentiable Simulation","created":"2024-04-03","cited_by_count":8},{"id":"2311.00802","title":"Neural Field Dynamics Model for Granular Object Piles Manipulation","created":"2023-11-01","cited_by_count":7},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6},{"id":"2203.10263","title":"DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting","created":"2022-03-19","cited_by_count":6},{"id":"2110.15326","title":"GOMP-FIT: Grasp-Optimized Motion Planning for Fast Inertial Transport","created":"2021-10-28","cited_by_count":4},{"id":"2404.00451","title":"Thin-Shell Object Manipulations With Differentiable Physics Simulations","created":"2024-03-30","cited_by_count":3}],"next_cursor":null}