{"list":"other","total":54,"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":"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":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"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":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"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":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"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":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2002.02794","title":"Reward-Free Exploration for Reinforcement Learning","created":"2020-02-07","cited_by_count":177},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"1903.01672","title":"Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes","created":"2019-03-05","cited_by_count":166},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"2209.08037","title":"DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization","created":"2022-09-16","cited_by_count":140},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108},{"id":"2006.06294","title":"Adaptive Reward-Free Exploration","created":"2020-06-11","cited_by_count":77},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74},{"id":"1909.11639","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","created":"2019-09-25","cited_by_count":72},{"id":"2106.13687","title":"panda-gym: Open-source goal-conditioned environments for robotic learning","created":"2021-06-25","cited_by_count":59},{"id":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45},{"id":"1905.08786","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","created":"2019-05-21","cited_by_count":40},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22},{"id":"2006.01419","title":"Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration","created":"2020-06-02","cited_by_count":20},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20},{"id":"2311.10747","title":"Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving","created":"2023-10-31","cited_by_count":17},{"id":"2006.02579","title":"Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains","created":"2020-06-03","cited_by_count":11},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4}],"next_cursor":null}