{"list":"other","total":53,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"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":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1702.02453","title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","created":"2017-02-08","cited_by_count":141},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60},{"id":"1806.07377","title":"Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation","created":"2018-05-31","cited_by_count":50},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41},{"id":"1907.11740","title":"Environment Probing Interaction Policies","created":"2019-07-26","cited_by_count":39},{"id":"2010.04893","title":"Trust the Model When It Is Confident: Masked Model-based Actor-Critic","created":"2020-10-10","cited_by_count":36},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"2207.06572","title":"i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops","created":"2022-07-14","cited_by_count":32},{"id":"2003.01709","title":"Hierarchically Decoupled Imitation for Morphological Transfer","created":"2020-03-03","cited_by_count":31},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31},{"id":"1903.11774","title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","created":"2019-03-28","cited_by_count":25},{"id":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21},{"id":"1909.13111","title":"MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics","created":"2019-09-28","cited_by_count":18},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17},{"id":"1708.04352","title":"Benchmark Environments for Multitask Learning in Continuous Domains","created":"2017-08-14","cited_by_count":14},{"id":"1910.10537","title":"Robust Visual Domain Randomization for Reinforcement Learning","created":"2019-10-23","cited_by_count":13},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13},{"id":"2107.00339","title":"Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding","created":"2021-07-01","cited_by_count":12},{"id":"2408.12970","title":"SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning","created":"2024-08-23","cited_by_count":12},{"id":"2310.15017","title":"Mind the Model, Not the Agent: The Primacy Bias in Model-based RL","created":"2023-10-23","cited_by_count":9},{"id":"1910.00105","title":"Domain Adaptive Imitation Learning","created":"2019-09-30","cited_by_count":6},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5},{"id":"2003.01369","title":"Traversing the Reality Gap via Simulator Tuning","created":"2020-03-03","cited_by_count":4},{"id":"2008.01594","title":"An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch","created":"2020-08-04","cited_by_count":3},{"id":"2111.08819","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","created":"2021-11-16","cited_by_count":3},{"id":"2312.15474","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","created":"2023-12-24","cited_by_count":3}],"next_cursor":null}