{"list":"other","total":66,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"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":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"1708.09251","title":"Quality and Diversity Optimization: A Unifying Modular Framework","created":"2017-05-12","cited_by_count":113},{"id":"1709.00084","title":"Behavior Trees in Robotics and AI: An Introduction","created":"2017-08-31","cited_by_count":107},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"2008.06389","title":"Sample-efficient Cross-Entropy Method for Real-time Planning","created":"2020-08-14","cited_by_count":95},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"1810.01222","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","created":"2018-10-02","cited_by_count":58},{"id":"1810.03779","title":"Reinforcement Learning for Improving Agent Design","created":"2018-10-09","cited_by_count":56},{"id":"1804.02395","title":"Structured Evolution with Compact Architectures for Scalable Policy Optimization","created":"2018-04-06","cited_by_count":48},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"2202.03666","title":"Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning","created":"2022-02-08","cited_by_count":38},{"id":"1905.00976","title":"Collaborative Evolutionary Reinforcement Learning","created":"2019-05-02","cited_by_count":37},{"id":"1911.06832","title":"Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning","created":"2019-11-15","cited_by_count":37},{"id":"2004.08763","title":"Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization","created":"2020-04-19","cited_by_count":32},{"id":"2009.01555","title":"Sample-Efficient Automated Deep Reinforcement Learning","created":"2020-09-03","cited_by_count":32},{"id":"1802.08842","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","created":"2018-02-24","cited_by_count":28},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28},{"id":"1906.09807","title":"Proximal Distilled Evolutionary Reinforcement Learning","created":"2019-06-24","cited_by_count":27},{"id":"1905.04100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","created":"2019-02-19","cited_by_count":24},{"id":"2001.02907","title":"Population-Guided Parallel Policy Search for Reinforcement Learning","created":"2020-01-09","cited_by_count":21},{"id":"2009.08973","title":"GRAC: Self-Guided and Self-Regularized Actor-Critic","created":"2020-09-18","cited_by_count":21},{"id":"1903.10605","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","created":"2019-03-25","cited_by_count":18},{"id":"1712.06563","title":"Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients","created":"2017-12-18","cited_by_count":15},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15},{"id":"2201.00129","title":"A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning","created":"2022-01-01","cited_by_count":13},{"id":"2012.05417","title":"An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search","created":"2020-12-10","cited_by_count":12},{"id":"2006.07554","title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","created":"2020-06-13","cited_by_count":11},{"id":"1803.04706","title":"Policy Search in Continuous Action Domains: an Overview","created":"2018-03-13","cited_by_count":10},{"id":"1903.01886","title":"Genetic-Gated Networks for Deep Reinforcement","created":"2018-11-26","cited_by_count":8},{"id":"2011.00791","title":"Cooperative Heterogeneous Deep Reinforcement Learning","created":"2020-11-02","cited_by_count":8},{"id":"1811.10264","title":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments","created":"2018-11-26","cited_by_count":7},{"id":"2006.06600","title":"Zeroth-Order Supervised Policy Improvement","created":"2020-06-11","cited_by_count":7},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7},{"id":"1909.07543","title":"Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning","created":"2019-09-17","cited_by_count":6},{"id":"2007.04725","title":"EVO-RL: Evolutionary-Driven Reinforcement Learning","created":"2020-07-09","cited_by_count":6},{"id":"1907.00526","title":"FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control","created":"2019-07-01","cited_by_count":5},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5},{"id":"2112.11115","title":"Soft Actor-Critic with Cross-Entropy Policy Optimization","created":"2021-12-21","cited_by_count":5},{"id":"1810.08102","title":"First-order and second-order variants of the gradient descent in a unified framework","created":"2018-10-18","cited_by_count":3},{"id":"1912.06310","title":"Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning","created":"2019-12-13","cited_by_count":3},{"id":"2002.09077","title":"Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy","created":"2020-02-21","cited_by_count":3},{"id":"2105.07960","title":"Behavior-based Neuroevolutionary Training in Reinforcement Learning","created":"2021-05-17","cited_by_count":3},{"id":"2201.09568","title":"Pearl: Parallel Evolutionary and Reinforcement Learning Library","created":"2022-01-24","cited_by_count":3},{"id":"2006.10887","title":"An adaptive stochastic gradient-free approach for high-dimensional blackbox optimization","created":"2020-06-18","cited_by_count":2},{"id":"1911.10527","title":"Merging Deterministic Policy Gradient Estimations with Varied Bias-Variance Tradeoff for Effective Deep Reinforcement Learning","created":"2019-11-24","cited_by_count":1},{"id":"2012.11692","title":"Evolving the Behavior of Machines: From Micro to Macroevolution","created":"2020-12-21","cited_by_count":1}],"next_cursor":null}