{"list":"other","total":74,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"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":"1812.02900","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":"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":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"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":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1605.06432","title":"Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data","created":"2016-05-20","cited_by_count":156},{"id":"1709.07857","title":"Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping","created":"2017-09-22","cited_by_count":144},{"id":"2006.16908","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","created":"2020-06-30","cited_by_count":142},{"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":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"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":"2012.11547","title":"Offline Reinforcement Learning from Images with Latent Space Models","created":"2020-12-21","cited_by_count":95},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"1902.00183","title":"Learning Action Representations for Reinforcement Learning","created":"2019-02-01","cited_by_count":75},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75},{"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":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54},{"id":"1911.12905","title":"Simulation-based reinforcement learning for real-world autonomous driving","created":"2019-11-29","cited_by_count":52},{"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":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44},{"id":"2012.09811","title":"Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency","created":"2020-12-17","cited_by_count":43},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42},{"id":"1907.11740","title":"Environment Probing Interaction Policies","created":"2019-07-26","cited_by_count":39},{"id":"2003.01629","title":"Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?","created":"2020-03-03","cited_by_count":37},{"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":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36},{"id":"1908.09357","title":"Dynamics-aware Embeddings","created":"2019-08-25","cited_by_count":34},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"2010.07470","title":"Masked Contrastive Representation Learning for Reinforcement Learning","created":"2020-10-15","cited_by_count":32},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32},{"id":"1906.08312","title":"Calibrated Model-Based Deep Reinforcement Learning","created":"2019-06-19","cited_by_count":31},{"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":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27},{"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":"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":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19},{"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":"2202.05244","title":"REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer","created":"2022-02-10","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":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12},{"id":"2212.07398","title":"Policy Adaptation from Foundation Model Feedback","created":"2022-12-14","cited_by_count":10},{"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":"2210.00350","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","created":"2022-10-01","cited_by_count":5},{"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}],"next_cursor":null}