{"list":"other","total":67,"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":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"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":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1705.07798","title":"A unified view of entropy-regularized Markov decision processes","created":"2017-05-22","cited_by_count":182},{"id":"1605.02097","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","created":"2016-05-06","cited_by_count":179},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"1607.00215","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","created":"2016-07-01","cited_by_count":117},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1703.00956","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","created":"2017-03-02","cited_by_count":110},{"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":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"1710.09767","title":"Meta Learning Shared Hierarchies","created":"2017-10-26","cited_by_count":93},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1910.12807","title":"Better Exploration with Optimistic Actor-Critic","created":"2019-10-28","cited_by_count":88},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","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":"1909.10618","title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?","created":"2019-09-23","cited_by_count":68},{"id":"1802.04412","title":"Efficient Exploration through Bayesian Deep Q-Networks","created":"2018-02-13","cited_by_count":67},{"id":"1802.04020","title":"Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning","created":"2018-02-12","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":"1901.09311","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","created":"2019-01-27","cited_by_count":55},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"1803.01118","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","created":"2018-03-03","cited_by_count":44},{"id":"1703.01260","title":"EX2: Exploration with Exemplar Models for Deep Reinforcement Learning","created":"2017-03-03","cited_by_count":42},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"1709.06293","title":"Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning","created":"2017-09-19","cited_by_count":37},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"2010.11151","title":"Logistic Q-Learning","created":"2020-10-21","cited_by_count":34},{"id":"1903.00606","title":"Discovering Options for Exploration by Minimizing Cover Time","created":"2019-03-02","cited_by_count":31},{"id":"2006.01782","title":"Temporally-Extended {\\epsilon}-Greedy Exploration","created":"2020-06-02","cited_by_count":29},{"id":"2002.12174","title":"Optimistic Exploration even with a Pessimistic Initialisation","created":"2020-02-26","cited_by_count":25},{"id":"1301.3878","title":"PEGASUS: A Policy Search Method for Large MDPs and POMDPs","created":"2013-01-16","cited_by_count":22},{"id":"1301.6690","title":"Model-Based Bayesian Exploration","created":"2013-01-23","cited_by_count":21},{"id":"1902.00843","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","created":"2019-02-03","cited_by_count":18},{"id":"1302.2550","title":"Online Regret Bounds for Undiscounted Continuous Reinforcement Learning","created":"2013-02-11","cited_by_count":17},{"id":"1806.02315","title":"Randomized Value Functions via Multiplicative Normalizing Flows","created":"2018-06-06","cited_by_count":15},{"id":"1905.12425","title":"Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities","created":"2019-05-27","cited_by_count":15},{"id":"2012.13658","title":"Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards","created":"2020-12-26","cited_by_count":13},{"id":"1803.05044","title":"Learning to Explore with Meta-Policy Gradient","created":"2018-03-13","cited_by_count":9},{"id":"1811.06629","title":"Context-Dependent Upper-Confidence Bounds for Directed Exploration","created":"2018-11-15","cited_by_count":3}],"next_cursor":null}