{"list":"other","total":87,"rows":[{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1906.01563","title":"Hamiltonian Neural Networks","created":"2019-06-04","cited_by_count":712},{"id":"2201.05624","title":"Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next","created":"2022-01-14","cited_by_count":608},{"id":"2003.04630","title":"Lagrangian Neural Networks","created":"2020-03-10","cited_by_count":398},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2104.13906","title":"Reward (Mis)design for Autonomous Driving","created":"2021-04-28","cited_by_count":104},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"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":"2109.06697","title":"Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions","created":"2021-09-14","cited_by_count":94},{"id":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77},{"id":"2004.07584","title":"Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions","created":"2020-04-16","cited_by_count":68},{"id":"1905.10866","title":"Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction","created":"2019-05-26","cited_by_count":67},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59},{"id":"2012.02788","title":"Neural Dynamic Policies for End-to-End Sensorimotor Learning","created":"2020-12-04","cited_by_count":58},{"id":"1911.12905","title":"Simulation-based reinforcement learning for real-world autonomous driving","created":"2019-11-29","cited_by_count":52},{"id":"2103.16021","title":"Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact","created":"2021-03-30","cited_by_count":52},{"id":"1812.10972","title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","created":"2018-12-28","cited_by_count":51},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50},{"id":"1711.09874","title":"Divide-and-Conquer Reinforcement Learning","created":"2017-11-27","cited_by_count":48},{"id":"1803.05580","title":"Feedback Control For Cassie With Deep Reinforcement Learning","created":"2018-03-15","cited_by_count":45},{"id":"2110.15344","title":"Learning to Jump from Pixels","created":"2021-10-28","cited_by_count":45},{"id":"2001.00449","title":"Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics","created":"2020-01-02","cited_by_count":44},{"id":"2010.09469","title":"A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries","created":"2020-10-15","cited_by_count":44},{"id":"1907.11740","title":"Environment Probing Interaction Policies","created":"2019-07-26","cited_by_count":39},{"id":"1402.0560","title":"Safe Exploration of State and Action Spaces in Reinforcement Learning","created":"2014-02-04","cited_by_count":38},{"id":"2008.03285","title":"Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning","created":"2020-08-07","cited_by_count":37},{"id":"2106.05863","title":"Learning Functional Priors and Posteriors from Data and Physics","created":"2021-06-08","cited_by_count":37},{"id":"1905.06841","title":"Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems","created":"2019-05-13","cited_by_count":33},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32},{"id":"2305.18035","title":"Physics-Informed Computer Vision: A Review and Perspectives","created":"2023-05-29","cited_by_count":28},{"id":"2011.01734","title":"Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning","created":"2020-11-03","cited_by_count":27},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23},{"id":"2210.15185","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","created":"2022-10-27","cited_by_count":22},{"id":"2305.10399","title":"End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics","created":"2023-05-17","cited_by_count":22},{"id":"1903.09885","title":"Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions","created":"2019-03-23","cited_by_count":21},{"id":"2011.04741","title":"Learning Task Space Actions for Bipedal Locomotion","created":"2020-11-09","cited_by_count":21},{"id":"1801.09627","title":"Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation","created":"2018-01-29","cited_by_count":18},{"id":"1901.04878","title":"Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems","created":"2019-01-15","cited_by_count":18},{"id":"2212.02179","title":"Physics-Informed Model-Based Reinforcement Learning","created":"2022-12-05","cited_by_count":18},{"id":"1803.10371","title":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system","created":"2018-03-28","cited_by_count":17},{"id":"2107.05627","title":"Hierarchical Neural Dynamic Policies","created":"2021-07-12","cited_by_count":17},{"id":"2102.10643","title":"Safe Reinforcement Learning Using Robust Action Governor","created":"2021-02-21","cited_by_count":14},{"id":"2305.09793","title":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","created":"2023-05-16","cited_by_count":13},{"id":"2104.08171","title":"Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions","created":"2021-04-16","cited_by_count":11},{"id":"2301.00641","title":"Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management","created":"2022-12-29","cited_by_count":11},{"id":"2103.12553","title":"Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions","created":"2021-03-23","cited_by_count":10},{"id":"1509.06824","title":"Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration","created":"2015-09-23","cited_by_count":8},{"id":"1808.04464","title":"On Passivity, Reinforcement Learning and Higher-Order Learning in Multi-Agent Finite Games","created":"2018-08-13","cited_by_count":8},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8},{"id":"1905.09700","title":"Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces","created":"2019-05-23","cited_by_count":7},{"id":"1906.01626","title":"Encoding Invariances in Deep Generative Models","created":"2019-06-04","cited_by_count":7},{"id":"2302.00237","title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)","created":"2023-02-01","cited_by_count":7},{"id":"1804.00198","title":"Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning","created":"2018-03-31","cited_by_count":6},{"id":"2011.04837","title":"Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation","created":"2020-11-10","cited_by_count":5},{"id":"1605.05835","title":"Experimental Demonstration of Frequency Regulation by Commercial Buildings - Part I: Modeling and Hierarchical Control Design","created":"2016-05-19","cited_by_count":4},{"id":"2210.00211","title":"Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States","created":"2022-10-01","cited_by_count":3},{"id":"2303.16860","title":"Physical Deep Reinforcement Learning Towards Safety Guarantee","created":"2023-03-29","cited_by_count":3},{"id":"1908.02750","title":"A physics-informed reinforcement learning approach for the interfacial area transport in two-phase flow","created":"2019-08-06","cited_by_count":2},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","cited_by_count":2},{"id":"2211.11830","title":"PhysQ: A Physics Informed Reinforcement Learning Framework for Building Control","created":"2022-11-21","cited_by_count":2},{"id":"2212.00618","title":"Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging","created":"2022-12-01","cited_by_count":1}],"next_cursor":null}