{"list":"other","total":65,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"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":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1911.09291","title":"Scalable methods for computing state similarity in deterministic Markov Decision Processes","created":"2019-11-21","cited_by_count":133},{"id":"1806.07851","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","created":"2018-06-20","cited_by_count":131},{"id":"1609.07088","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","created":"2016-09-22","cited_by_count":127},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"1603.08029","title":"Resnet in Resnet: Generalizing Residual Architectures","created":"2016-03-25","cited_by_count":110},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"2006.13900","title":"Quantifying Differences in Reward Functions","created":"2020-06-24","cited_by_count":63},{"id":"2006.16232","title":"Learning Robot Skills with Temporal Variational Inference","created":"2020-06-29","cited_by_count":54},{"id":"2001.01102","title":"MushroomRL: Simplifying Reinforcement Learning Research","created":"2020-01-04","cited_by_count":50},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49},{"id":"1811.00260","title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","created":"2018-11-01","cited_by_count":48},{"id":"2007.12540","title":"Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference","created":"2020-07-24","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":"1905.01756","title":"P3O: Policy-on Policy-off Policy Optimization","created":"2019-05-05","cited_by_count":37},{"id":"2402.19249","title":"Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting","created":"2024-02-29","cited_by_count":36},{"id":"2011.00401","title":"The MAGICAL Benchmark for Robust Imitation","created":"2020-11-01","cited_by_count":32},{"id":"2003.01709","title":"Hierarchically Decoupled Imitation for Morphological Transfer","created":"2020-03-03","cited_by_count":31},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16},{"id":"1703.07261","title":"Black-Box Data-efficient Policy Search for Robotics","created":"2017-03-21","cited_by_count":14},{"id":"2011.11827","title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning","created":"2020-11-24","cited_by_count":14},{"id":"2209.12093","title":"Learn what matters: cross-domain imitation learning with task-relevant embeddings","created":"2022-09-24","cited_by_count":14},{"id":"2305.14792","title":"ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters","created":"2023-05-24","cited_by_count":12},{"id":"2302.05614","title":"Cross-domain Random Pre-training with Prototypes for Reinforcement Learning","created":"2023-02-11","cited_by_count":9},{"id":"2006.07041","title":"Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch","created":"2020-06-12","cited_by_count":8},{"id":"2304.03833","title":"Learning Robot Manipulation from Cross-Morphology Demonstration","created":"2023-04-07","cited_by_count":8},{"id":"2309.17046","title":"CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning","created":"2023-09-29","cited_by_count":8},{"id":"2105.14780","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","created":"2021-05-31","cited_by_count":7},{"id":"2203.00904","title":"Weakly Supervised Correspondence Learning","created":"2022-03-02","cited_by_count":7},{"id":"1801.06920","title":"Cross-Domain Transfer in Reinforcement Learning using Target Apprentice","created":"2018-01-22","cited_by_count":6},{"id":"2202.02967","title":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","created":"2022-02-07","cited_by_count":5},{"id":"2312.03764","title":"Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning","created":"2023-12-05","cited_by_count":4},{"id":"1908.05265","title":"Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity","created":"2019-08-14","cited_by_count":3},{"id":"2103.10642","title":"Knowledge-Based Hierarchical POMDPs for Task Planning","created":"2021-03-19","cited_by_count":3},{"id":"2302.13442","title":"Understanding URDF: A Survey Based on User Experience","created":"2023-02-26","cited_by_count":3},{"id":"2310.13458","title":"Correspondence learning between morphologically different robots via task demonstrations","created":"2023-10-20","cited_by_count":2}],"next_cursor":null}