{"list":"other","total":52,"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"1806.05618","title":"Stochastic Variance-Reduced Policy Gradient","created":"2018-06-14","cited_by_count":106},{"id":"1911.02140","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","created":"2019-11-05","cited_by_count":88},{"id":"1909.12238","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","created":"2019-09-26","cited_by_count":85},{"id":"1903.07940","title":"Truly Proximal Policy Optimization","created":"2019-03-19","cited_by_count":69},{"id":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55},{"id":"1911.03618","title":"Worst Cases Policy Gradients","created":"2019-11-09","cited_by_count":52},{"id":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17},{"id":"2210.01041","title":"Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models","created":"2022-10-03","cited_by_count":15},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13},{"id":"2209.06896","title":"Persistently Feasible Robust Safe Control by Safety Index Synthesis and Convex Semi-Infinite Programming","created":"2022-09-14","cited_by_count":12},{"id":"2209.09134","title":"Safety Index Synthesis via Sum-of-Squares Programming","created":"2022-09-19","cited_by_count":12},{"id":"2306.17279","title":"Probabilistic Constraint for Safety-Critical Reinforcement Learning","created":"2023-06-29","cited_by_count":11},{"id":"1902.02823","title":"Compatible Natural Gradient Policy Search","created":"2019-02-07","cited_by_count":10},{"id":"2102.01985","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","created":"2021-02-03","cited_by_count":10},{"id":"2306.12594","title":"State-wise Constrained Policy Optimization","created":"2023-06-21","cited_by_count":9},{"id":"1710.06034","title":"Stochastic Variance Reduction for Policy Gradient Estimation","created":"2017-10-17","cited_by_count":8},{"id":"1912.09095","title":"Safe Adaptation with Multiplicative Uncertainties Using Robust Safe Set Algorithm","created":"2019-12-19","cited_by_count":8},{"id":"1905.08152","title":"Stochastic Variance Reduction for Deep Q-learning","created":"2019-05-20","cited_by_count":7},{"id":"2001.09550","title":"Experimental Evaluation of Human Motion Prediction: Toward Safe and Efficient Human Robot Collaboration","created":"2020-01-27","cited_by_count":7},{"id":"2301.10932","title":"On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures","created":"2023-01-26","cited_by_count":7},{"id":"2104.08896","title":"Provably Safe Tolerance Estimation for Robot Arms via Sum-of-Squares Programming","created":"2021-04-18","cited_by_count":6},{"id":"2308.13140","title":"Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization","created":"2023-08-25","cited_by_count":4},{"id":"1910.03857","title":"Policy Optimization Through Approximate Importance Sampling","created":"2019-10-09","cited_by_count":3},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3},{"id":"2012.02439","title":"Proximal Policy Optimization Smoothed Algorithm","created":"2020-12-04","cited_by_count":2},{"id":"2307.16152","title":"Variance Control for Distributional Reinforcement Learning","created":"2023-07-30","cited_by_count":2},{"id":"2302.07985","title":"Trust-Region-Free Policy Optimization for Stochastic Policies","created":"2023-02-15","cited_by_count":1}],"next_cursor":null}