{"list":"other","total":74,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2208.06193","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","created":"2022-08-12","cited_by_count":562},{"id":"2112.07804","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","created":"2021-12-15","cited_by_count":516},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89},{"id":"2006.09641","title":"Automatic Curriculum Learning through Value Disagreement","created":"2020-06-17","cited_by_count":87},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"id":"2006.13205","title":"Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors","created":"2020-06-23","cited_by_count":62},{"id":"2307.14326","title":"Waypoint-Based Imitation Learning for Robotic Manipulation","created":"2023-07-26","cited_by_count":61},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59},{"id":"1301.4862","title":"Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots","created":"2013-01-21","cited_by_count":58},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50},{"id":"2010.14274","title":"Behavior Priors for Efficient Reinforcement Learning","created":"2020-10-27","cited_by_count":41},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31},{"id":"1911.07224","title":"Learning from Trajectories via Subgoal Discovery","created":"2019-11-03","cited_by_count":28},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28},{"id":"1806.09605","title":"Many-Goals Reinforcement Learning","created":"2018-06-22","cited_by_count":22},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13},{"id":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","cited_by_count":7},{"id":"2305.08932","title":"MIMEx: Intrinsic Rewards from Masked Input Modeling","created":"2023-05-15","cited_by_count":6},{"id":"2303.05487","title":"Learning Rational Subgoals from Demonstrations and Instructions","created":"2023-03-09","cited_by_count":5}],"next_cursor":null}