{"list":"other","total":141,"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"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":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1810.05642","title":"The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems","created":"2018-10-11","cited_by_count":277},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"1804.02717","title":"DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills","created":"2018-04-08","cited_by_count":163},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"1910.09615","title":"IPO: Interior-point Policy Optimization under Constraints","created":"2019-10-21","cited_by_count":132},{"id":"1904.06457","title":"YouTube UGC Dataset for Video Compression Research","created":"2019-04-13","cited_by_count":124},{"id":"1803.08287","title":"Learning-based Model Predictive Control for Safe Exploration","created":"2018-03-22","cited_by_count":120},{"id":"2008.06626","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","created":"2020-08-15","cited_by_count":115},{"id":"2010.14497","title":"Conservative Safety Critics for Exploration","created":"2020-10-27","cited_by_count":113},{"id":"1803.08884","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","created":"2018-03-23","cited_by_count":106},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"1404.3862","title":"Optimizing the CVaR via Sampling","created":"2014-04-15","cited_by_count":99},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"2011.00583","title":"Game-Theoretic Multiagent Reinforcement Learning","created":"2020-11-01","cited_by_count":94},{"id":"1705.10702","title":"Cautious Model Predictive Control using Gaussian Process Regression","created":"2017-05-30","cited_by_count":91},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80},{"id":"1911.09101","title":"Safe Policies for Reinforcement Learning via Primal-Dual Methods","created":"2019-11-20","cited_by_count":79},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1709.07643","title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","created":"2017-09-22","cited_by_count":70},{"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":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"id":"1906.09323","title":"Reinforcement Learning with Convex Constraints","created":"2019-06-21","cited_by_count":60},{"id":"1910.12156","title":"Convergent Policy Optimization for Safe Reinforcement Learning","created":"2019-10-26","cited_by_count":57},{"id":"1912.03193","title":"Risk-Averse Trust Region Optimization for Reward-Volatility Reduction","created":"2019-12-06","cited_by_count":54},{"id":"1706.06491","title":"Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control","created":"2017-06-20","cited_by_count":53},{"id":"1910.00399","title":"Safe Reinforcement Learning on Autonomous Vehicles","created":"2019-09-27","cited_by_count":50},{"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":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47},{"id":"2002.12156","title":"Cautious Reinforcement Learning with Logical Constraints","created":"2020-02-26","cited_by_count":45},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45},{"id":"1909.03602","title":"DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems","created":"2019-09-09","cited_by_count":44},{"id":"2010.00587","title":"Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs","created":"2020-10-01","cited_by_count":42},{"id":"2101.10895","title":"A Primal-Dual Approach to Constrained Markov Decision Processes","created":"2021-01-26","cited_by_count":42},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40},{"id":"1609.01387","title":"Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework","created":"2016-09-06","cited_by_count":39},{"id":"1907.07273","title":"An Inductive Synthesis Framework for Verifiable Reinforcement Learning","created":"2019-07-16","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":"2011.04251","title":"Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships","created":"2020-11-09","cited_by_count":37},{"id":"1906.07772","title":"First-order methods almost always avoid saddle points: the case of vanishing step-sizes","created":"2019-06-18","cited_by_count":35},{"id":"2003.01303","title":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization","created":"2020-03-03","cited_by_count":35},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35},{"id":"2006.05051","title":"Constrained episodic reinforcement learning in concave-convex and knapsack settings","created":"2020-06-09","cited_by_count":34},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"2009.11348","title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints","created":"2020-09-23","cited_by_count":34},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33}],"next_cursor":"100"}