{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"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":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"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":"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":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"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":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"1703.01703","title":"Third-Person Imitation Learning","created":"2017-03-06","cited_by_count":103},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"1804.09364","title":"Driving Policy Transfer via Modularity and Abstraction","created":"2018-04-25","cited_by_count":92},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91},{"id":"2006.09001","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","created":"2020-06-16","cited_by_count":91},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"1704.03952","title":"Virtual to Real Reinforcement Learning for Autonomous Driving","created":"2017-04-13","cited_by_count":80},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"1911.09676","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","created":"2019-11-21","cited_by_count":73},{"id":"1911.10947","title":"State Alignment-based Imitation Learning","created":"2019-11-21","cited_by_count":73},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71},{"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":"1610.03518","title":"Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model","created":"2016-10-11","cited_by_count":54},{"id":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"2106.02377","title":"A Survey on Deep Domain Adaptation for LiDAR Perception","created":"2021-06-04","cited_by_count":47},{"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":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41},{"id":"1812.03823","title":"Learning to Drive from Simulation without Real World Labels","created":"2018-12-10","cited_by_count":39},{"id":"2002.11879","title":"State-only Imitation with Transition Dynamics Mismatch","created":"2020-02-27","cited_by_count":37},{"id":"1802.00265","title":"VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control","created":"2018-02-01","cited_by_count":35},{"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":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29},{"id":"2307.03719","title":"Polybot: Training One Policy Across Robots While Embracing Variability","created":"2023-07-07","cited_by_count":28},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","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":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23},{"id":"2212.07407","title":"Cross-Domain Transfer via Semantic Skill Imitation","created":"2022-12-14","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":"2209.12093","title":"Learn what matters: cross-domain imitation learning with task-relevant embeddings","created":"2022-09-24","cited_by_count":14},{"id":"2212.09078","title":"Multi-embodiment Legged Robot Control as a Sequence Modeling Problem","created":"2022-12-18","cited_by_count":11},{"id":"2110.15142","title":"Learning Feasibility to Imitate Demonstrators with Different Dynamics","created":"2021-10-28","cited_by_count":10},{"id":"2310.13914","title":"Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States","created":"2023-10-21","cited_by_count":10},{"id":"2304.03833","title":"Learning Robot Manipulation from Cross-Morphology Demonstration","created":"2023-04-07","cited_by_count":8},{"id":"2203.00904","title":"Weakly Supervised Correspondence Learning","created":"2022-03-02","cited_by_count":7},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5}],"next_cursor":null}