{"list":"other","total":59,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"1909.11652","title":"Deep Dynamics Models for Learning Dexterous Manipulation","created":"2019-09-25","cited_by_count":206},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"2101.02722","title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","created":"2021-01-07","cited_by_count":100},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99},{"id":"1907.13098","title":"Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks","created":"2019-07-28","cited_by_count":84},{"id":"2303.10880","title":"Rotating without Seeing: Towards In-hand Dexterity through Touch","created":"2023-03-20","cited_by_count":84},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2303.12076","title":"Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play","created":"2023-03-21","cited_by_count":62},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59},{"id":"2007.12401","title":"Predictive Information Accelerates Learning in RL","created":"2020-07-24","cited_by_count":56},{"id":"2312.01853","title":"Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing","created":"2023-12-04","cited_by_count":56},{"id":"2202.03825","title":"skrl: Modular and Flexible Library for Reinforcement Learning","created":"2022-02-08","cited_by_count":49},{"id":"2210.00121","title":"Visuo-Tactile Transformers for Manipulation","created":"2022-09-30","cited_by_count":47},{"id":"1502.02251","title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","created":"2015-02-08","cited_by_count":45},{"id":"1903.04128","title":"Manipulation by Feel: Touch-Based Control with Deep Predictive Models","created":"2019-03-11","cited_by_count":36},{"id":"2309.12300","title":"See to Touch: Learning Tactile Dexterity through Visual Incentives","created":"2023-09-21","cited_by_count":35},{"id":"2401.12024","title":"Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training","created":"2024-01-22","cited_by_count":31},{"id":"2312.13469","title":"Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation","created":"2023-12-20","cited_by_count":28},{"id":"2305.14133","title":"Conditional Mutual Information for Disentangled Representations in Reinforcement Learning","created":"2023-05-23","cited_by_count":27},{"id":"2311.00924","title":"The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning","created":"2023-11-02","cited_by_count":26},{"id":"2505.11164","title":"Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning","created":"2025-05-16","cited_by_count":26},{"id":"2101.11812","title":"SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation","created":"2021-01-28","cited_by_count":24},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24},{"id":"2405.07391","title":"AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touch","created":"2024-05-12","cited_by_count":21},{"id":"2204.03698","title":"Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand","created":"2022-04-07","cited_by_count":20},{"id":"2207.05480","title":"Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning","created":"2022-07-12","cited_by_count":19},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15},{"id":"1809.07004","title":"Leveraging Contact Forces for Learning to Grasp","created":"2018-09-19","cited_by_count":13},{"id":"2107.02339","title":"Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning","created":"2021-07-06","cited_by_count":13},{"id":"2304.00736","title":"TacGNN:Learning Tactile-based In-hand Manipulation with a Blind Robot","created":"2023-04-03","cited_by_count":11},{"id":"2102.11051","title":"Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation","created":"2021-02-22","cited_by_count":10},{"id":"2307.14272","title":"Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing","created":"2023-07-26","cited_by_count":10},{"id":"2302.05342","title":"Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL","created":"2023-02-10","cited_by_count":9},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8},{"id":"2206.11396","title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","created":"2022-06-22","cited_by_count":7},{"id":"1906.11951","title":"Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments","created":"2019-06-27","cited_by_count":4},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4}],"next_cursor":null}