{"list":"other","total":111,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1504.04909","title":"Illuminating search spaces by mapping elites","created":"2015-04-20","cited_by_count":425},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"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":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"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":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"1809.07803","title":"Dynamic Weights in Multi-Objective Deep Reinforcement Learning","created":"2018-09-20","cited_by_count":100},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"1803.03835","title":"Kickstarting Deep Reinforcement Learning","created":"2018-03-10","cited_by_count":81},{"id":"1906.04358","title":"Weight Agnostic Neural Networks","created":"2019-06-11","cited_by_count":71},{"id":"1809.10124","title":"Learning Navigation Behaviors End-to-End with AutoRL","created":"2018-09-26","cited_by_count":70},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"1610.05729","title":"Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm","created":"2016-10-18","cited_by_count":66},{"id":"1810.01222","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","created":"2018-10-02","cited_by_count":58},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"1905.11874","title":"Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors","created":"2019-05-28","cited_by_count":57},{"id":"1910.01215","title":"ES-MAML: Simple Hessian-Free Meta Learning","created":"2019-09-25","cited_by_count":57},{"id":"2203.15386","title":"Pareto Set Learning for Neural Multi-objective Combinatorial Optimization","created":"2022-03-29","cited_by_count":56},{"id":"2006.08505","title":"Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization","created":"2020-06-15","cited_by_count":54},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49},{"id":"1712.04170","title":"Interpretable Policies for Reinforcement Learning by Genetic Programming","created":"2017-12-12","cited_by_count":48},{"id":"1804.02395","title":"Structured Evolution with Compact Architectures for Scalable Policy Optimization","created":"2018-04-06","cited_by_count":48},{"id":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"2201.09863","title":"Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots","created":"2022-01-24","cited_by_count":47},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40},{"id":"2003.01825","title":"Scaling MAP-Elites to Deep Neuroevolution","created":"2020-03-03","cited_by_count":38},{"id":"1905.00976","title":"Collaborative Evolutionary Reinforcement Learning","created":"2019-05-02","cited_by_count":37},{"id":"2009.01555","title":"Sample-Efficient Automated Deep Reinforcement Learning","created":"2020-09-03","cited_by_count":32},{"id":"1905.07628","title":"Evolving Rewards to Automate Reinforcement Learning","created":"2019-05-18","cited_by_count":31},{"id":"1811.05931","title":"Evolving intrinsic motivations for altruistic behavior","created":"2018-11-14","cited_by_count":30},{"id":"2202.05008","title":"EvoJAX: Hardware-Accelerated Neuroevolution","created":"2022-02-10","cited_by_count":29},{"id":"1802.08842","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","created":"2018-02-24","cited_by_count":28},{"id":"1906.09807","title":"Proximal Distilled Evolutionary Reinforcement Learning","created":"2019-06-24","cited_by_count":27},{"id":"2009.13579","title":"Novelty Search in Representational Space for Sample Efficient Exploration","created":"2020-09-28","cited_by_count":26},{"id":"2003.05325","title":"Meta-learning curiosity algorithms","created":"2020-03-11","cited_by_count":25},{"id":"1712.06568","title":"ES Is More Than Just a Traditional Finite-Difference Approximator","created":"2017-12-18","cited_by_count":24},{"id":"1906.08857","title":"Deep Neuroevolution of Recurrent and Discrete World Models","created":"2019-04-28","cited_by_count":23},{"id":"2203.14009","title":"Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey","created":"2022-03-26","cited_by_count":23},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20},{"id":"1712.06564","title":"On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent","created":"2017-12-18","cited_by_count":16},{"id":"1410.7326","title":"Neuroevolution in Games: State of the Art and Open Challenges","created":"2014-10-27","cited_by_count":15},{"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":"1906.07315","title":"Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination","created":"2019-06-18","cited_by_count":14},{"id":"2008.04589","title":"Model-Based Quality-Diversity Search for Efficient Robot Learning","created":"2020-08-11","cited_by_count":14},{"id":"2109.06409","title":"Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion","created":"2021-09-14","cited_by_count":14},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14},{"id":"1810.06773","title":"Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks","created":"2018-10-16","cited_by_count":13},{"id":"2102.03140","title":"Sparse Reward Exploration via Novelty Search and Emitters","created":"2021-02-05","cited_by_count":13},{"id":"2109.13800","title":"Faster Improvement Rate Population Based Training","created":"2021-09-28","cited_by_count":13},{"id":"2201.00129","title":"A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning","created":"2022-01-01","cited_by_count":13},{"id":"1806.00553","title":"Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems","created":"2018-06-01","cited_by_count":12},{"id":"1807.02397","title":"Quality Diversity Through Surprise","created":"2018-07-06","cited_by_count":12},{"id":"1905.02363","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","created":"2019-05-07","cited_by_count":12},{"id":"2003.06212","title":"Accelerating and Improving AlphaZero Using Population Based Training","created":"2020-03-13","cited_by_count":12},{"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":"1806.07917","title":"Meta-Learning by the Baldwin Effect","created":"2018-06-06","cited_by_count":10},{"id":"1902.03142","title":"Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric Distance","created":"2019-02-08","cited_by_count":9},{"id":"2205.08189","title":"Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Search","created":"2022-05-17","cited_by_count":9},{"id":"1707.03902","title":"Autoencoder-augmented Neuroevolution for Visual Doom Playing","created":"2017-07-12","cited_by_count":8},{"id":"1806.05695","title":"Evolving simple programs for playing Atari games","created":"2018-06-14","cited_by_count":8},{"id":"2003.10306","title":"Safe Crossover of Neural Networks Through Neuron Alignment","created":"2020-03-23","cited_by_count":8},{"id":"2009.03603","title":"Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search","created":"2020-09-08","cited_by_count":8},{"id":"2109.06826","title":"Few-shot Quality-Diversity Optimization","created":"2021-09-14","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":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7},{"id":"2202.02790","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","created":"2022-02-06","cited_by_count":6},{"id":"2106.12659","title":"Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learning","created":"2021-06-23","cited_by_count":5},{"id":"1710.05958","title":"Gradient-free Policy Architecture Search and Adaptation","created":"2017-10-16","cited_by_count":4},{"id":"1910.12824","title":"Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control","created":"2019-10-28","cited_by_count":4}],"next_cursor":"100"}