{"list":"other","total":53,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","cited_by_count":89},{"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":"1905.06424","title":"Meta reinforcement learning as task inference","created":"2019-05-15","cited_by_count":77},{"id":"1606.02396","title":"Deep Successor Reinforcement Learning","created":"2016-06-08","cited_by_count":72},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"1806.04640","title":"Unsupervised Meta-Learning for Reinforcement Learning","created":"2018-06-12","cited_by_count":39},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"1806.02448","title":"Deep Reinforcement Learning for General Video Game AI","created":"2018-06-06","cited_by_count":25},{"id":"1803.00781","title":"Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration","created":"2018-03-02","cited_by_count":23},{"id":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23},{"id":"2106.00671","title":"What Can I Do Here? Learning New Skills by Imagining Visual Affordances","created":"2021-06-01","cited_by_count":23},{"id":"2010.13957","title":"MELD: Meta-Reinforcement Learning from Images via Latent State Models","created":"2020-10-26","cited_by_count":22},{"id":"1905.07447","title":"REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning","created":"2019-05-17","cited_by_count":17},{"id":"2005.02934","title":"Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization","created":"2020-05-06","cited_by_count":16},{"id":"2008.02598","title":"Offline Meta Learning of Exploration","created":"2020-08-06","cited_by_count":13},{"id":"1911.10866","title":"Disentangled Cumulants Help Successor Representations Transfer to New Tasks","created":"2019-11-25","cited_by_count":11},{"id":"1602.02261","title":"End-to-End Goal-Driven Web Navigation","created":"2016-02-06","cited_by_count":10}],"next_cursor":null}