{"list":"other","total":74,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"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":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"1902.08438","title":"Online Meta-Learning","created":"2019-02-22","cited_by_count":137},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1710.03641","title":"Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments","created":"2017-10-10","cited_by_count":108},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","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":"2010.05595","title":"Rethinking Experience Replay: a Bag of Tricks for Continual Learning","created":"2020-10-12","cited_by_count":94},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"2110.14565","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","created":"2021-10-27","cited_by_count":74},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"id":"1912.08866","title":"Continuous Meta-Learning without Tasks","created":"2019-12-18","cited_by_count":50},{"id":"1906.08387","title":"Experience Replay Optimization","created":"2019-06-19","cited_by_count":48},{"id":"1909.12995","title":"Learning Fast Adaptation with Meta Strategy Optimization","created":"2019-09-28","cited_by_count":48},{"id":"1807.05827","title":"Remember and Forget for Experience Replay","created":"2018-07-16","cited_by_count":43},{"id":"2003.01239","title":"Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning","created":"2020-03-02","cited_by_count":43},{"id":"2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","created":"2020-06-23","cited_by_count":42},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"1802.07442","title":"Learning to Play with Intrinsically-Motivated Self-Aware Agents","created":"2018-02-21","cited_by_count":35},{"id":"2007.02418","title":"Selective Dyna-style Planning Under Limited Model Capacity","created":"2020-07-05","cited_by_count":30},{"id":"2007.07853","title":"Active World Model Learning with Progress Curiosity","created":"2020-07-15","cited_by_count":28},{"id":"2102.04736","title":"Reverb: A Framework For Experience Replay","created":"2021-02-09","cited_by_count":27},{"id":"1805.09692","title":"Been There, Done That: Meta-Learning with Episodic Recall","created":"2018-05-24","cited_by_count":26},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25},{"id":"2301.06294","title":"Neuro-Symbolic World Models for Adapting to Open World Novelty","created":"2023-01-16","cited_by_count":14},{"id":"2007.03158","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","created":"2020-07-07","cited_by_count":11},{"id":"2007.07358","title":"Learning to Sample with Local and Global Contexts in Experience Replay Buffer","created":"2020-07-14","cited_by_count":10},{"id":"2204.11464","title":"Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods","created":"2022-04-25","cited_by_count":10},{"id":"1609.06757","title":"Quickest Change Detection Approach to Optimal Control in Markov Decision Processes with Model Changes","created":"2016-09-21","cited_by_count":8},{"id":"2002.05822","title":"Frequency-based Search-control in Dyna","created":"2020-02-14","cited_by_count":7},{"id":"2011.07318","title":"A Geometric Perspective on Self-Supervised Policy Adaptation","created":"2020-11-14","cited_by_count":4}],"next_cursor":null}