{"list":"other","total":113,"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":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"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":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1504.04909","title":"Illuminating search spaces by mapping elites","created":"2015-04-20","cited_by_count":425},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"2005.04269","title":"Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics","created":"2020-05-08","cited_by_count":165},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"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":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"2111.00053","title":"Symbolic Regression via Neural-Guided Genetic Programming Population Seeding","created":"2021-10-29","cited_by_count":101},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"1902.05570","title":"Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems","created":"2019-02-13","cited_by_count":90},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2002.03939","title":"Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":81},{"id":"2309.14032","title":"DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization","created":"2023-09-25","cited_by_count":78},{"id":"2106.03894","title":"Differentiable Quality Diversity","created":"2021-06-07","cited_by_count":72},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59},{"id":"1810.01222","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","created":"2018-10-02","cited_by_count":58},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58},{"id":"1901.11454","title":"Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning","created":"2019-01-31","cited_by_count":57},{"id":"2006.08505","title":"Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization","created":"2020-06-15","cited_by_count":54},{"id":"2008.10066","title":"Learning Off-Policy with Online Planning","created":"2020-08-23","cited_by_count":53},{"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":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"1910.01465","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","created":"2019-10-03","cited_by_count":47},{"id":"2201.09863","title":"Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots","created":"2022-01-24","cited_by_count":47},{"id":"1905.08006","title":"Deep Reinforcement Learning Based Parameter Control in Differential Evolution","created":"2019-05-20","cited_by_count":38},{"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":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36},{"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":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29},{"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":"2007.15724","title":"MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments","created":"2020-07-30","cited_by_count":26},{"id":"2002.03950","title":"Q-value Path Decomposition for Deep Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":24},{"id":"2006.09226","title":"Parameter-Based Value Functions","created":"2020-06-16","cited_by_count":24},{"id":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24},{"id":"2203.08553","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","created":"2022-03-16","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":"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":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16},{"id":"2210.13156","title":"Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains","created":"2022-10-24","cited_by_count":15},{"id":"2305.05909","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","created":"2023-05-10","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":"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":"2201.00129","title":"A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning","created":"2022-01-01","cited_by_count":13},{"id":"1903.09688","title":"Symbolic Regression Methods for Reinforcement Learning","created":"2019-03-22","cited_by_count":11},{"id":"2006.07554","title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","created":"2020-06-13","cited_by_count":11},{"id":"1702.07490","title":"Online Meta-learning by Parallel Algorithm Competition","created":"2017-02-24","cited_by_count":9},{"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":"2206.05694","title":"RL-GA: A Reinforcement Learning-Based Genetic Algorithm for Electromagnetic Detection Satellite Scheduling Problem","created":"2022-06-12","cited_by_count":8},{"id":"2210.00498","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","created":"2022-10-02","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":"2208.12758","title":"Quality Diversity Evolutionary Learning of Decision Trees","created":"2022-08-17","cited_by_count":7},{"id":"2302.10145","title":"Improving Deep Policy Gradients with Value Function Search","created":"2023-02-20","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":"2303.06164","title":"Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning","created":"2023-03-10","cited_by_count":6},{"id":"2305.05116","title":"Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation","created":"2023-05-09","cited_by_count":6}],"next_cursor":"100"}