{"list":"other","total":56,"rows":[{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1504.04909","title":"Illuminating search spaces by mapping elites","created":"2015-04-20","cited_by_count":425},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"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":"2007.02151","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","created":"2020-07-04","cited_by_count":111},{"id":"1901.10964","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","created":"2019-01-30","cited_by_count":88},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"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":"2004.09468","title":"Real World Games Look Like Spinning Tops","created":"2020-04-20","cited_by_count":66},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"id":"1905.11874","title":"Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors","created":"2019-05-28","cited_by_count":57},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","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":"2001.01394","title":"A Boolean Task Algebra for Reinforcement Learning","created":"2020-01-06","cited_by_count":48},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39},{"id":"2202.03666","title":"Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning","created":"2022-02-08","cited_by_count":38},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37},{"id":"1906.00088","title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","created":"2019-05-31","cited_by_count":34},{"id":"2012.07827","title":"Relative Variational Intrinsic Control","created":"2020-12-14","cited_by_count":34},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28},{"id":"2303.07462","title":"Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty","created":"2023-03-13","cited_by_count":27},{"id":"2004.09677","title":"Approximate exploitability: Learning a best response in large games","created":"2020-04-20","cited_by_count":23},{"id":"2102.04323","title":"Discovering a set of policies for the worst case reward","created":"2021-02-08","cited_by_count":21},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17},{"id":"2303.08060","title":"Beyond Games: A Systematic Review of Neural Monte Carlo Tree Search Applications","created":"2023-03-14","cited_by_count":16},{"id":"2009.04374","title":"Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess","created":"2020-09-09","cited_by_count":15},{"id":"2112.15025","title":"Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates","created":"2021-12-30","cited_by_count":14},{"id":"2202.07415","title":"NeuPL: Neural Population Learning","created":"2022-02-15","cited_by_count":14},{"id":"1911.01679","title":"Apprenticeship Learning via Frank-Wolfe","created":"2019-11-05","cited_by_count":13},{"id":"2006.07781","title":"Non-local Policy Optimization via Diversity-regularized Collaborative Exploration","created":"2020-06-14","cited_by_count":13},{"id":"1905.09710","title":"Inverse Reinforcement Learning in Contextual MDPs","created":"2019-05-23","cited_by_count":12},{"id":"2005.10696","title":"Novel Policy Seeking with Constrained Optimization","created":"2020-05-21","cited_by_count":11},{"id":"2110.11737","title":"Measuring the Non-Transitivity in Chess","created":"2021-10-22","cited_by_count":10},{"id":"2205.15879","title":"Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games","created":"2022-05-31","cited_by_count":8},{"id":"1804.03176","title":"Frank-Wolfe Splitting via Augmented Lagrangian Method","created":"2018-04-09","cited_by_count":7},{"id":"1902.10140","title":"Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies","created":"2019-02-26","cited_by_count":5}],"next_cursor":null}