{"list":"other","total":70,"rows":[{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"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":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1810.13400","title":"Differentiable MPC for End-to-end Planning and Control","created":"2018-10-31","cited_by_count":189},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"2002.04523","title":"Objective Mismatch in Model-based Reinforcement Learning","created":"2020-02-11","cited_by_count":96},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2110.14565","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","created":"2021-10-27","cited_by_count":74},{"id":"2004.07804","title":"A Game Theoretic Framework for Model Based Reinforcement Learning","created":"2020-04-16","cited_by_count":73},{"id":"2007.14535","title":"Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction","created":"2020-07-29","cited_by_count":66},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2011.04021","title":"On the role of planning in model-based deep reinforcement learning","created":"2020-11-08","cited_by_count":57},{"id":"1902.01240","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","created":"2019-02-04","cited_by_count":56},{"id":"2106.07156","title":"Temporal Predictive Coding For Model-Based Planning In Latent Space","created":"2021-06-14","cited_by_count":55},{"id":"2008.10066","title":"Learning Off-Policy with Online Planning","created":"2020-08-23","cited_by_count":53},{"id":"1802.03006","title":"Learning and Querying Fast Generative Models for Reinforcement Learning","created":"2018-02-08","cited_by_count":48},{"id":"2008.12775","title":"On the model-based stochastic value gradient for continuous reinforcement learning","created":"2020-08-28","cited_by_count":47},{"id":"2010.14496","title":"Generative Temporal Difference Learning for Infinite-Horizon Prediction","created":"2020-10-27","cited_by_count":45},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32},{"id":"1906.10667","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","created":"2019-06-25","cited_by_count":30},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29},{"id":"2006.04363","title":"Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models","created":"2020-06-08","cited_by_count":28},{"id":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27},{"id":"2003.00030","title":"Policy-Aware Model Learning for Policy Gradient Methods","created":"2020-02-28","cited_by_count":23},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"2011.13897","title":"Latent Skill Planning for Exploration and Transfer","created":"2020-11-27","cited_by_count":19},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19},{"id":"1706.09597","title":"Path Integral Networks: End-to-End Differentiable Optimal Control","created":"2017-06-29","cited_by_count":16},{"id":"2010.09546","title":"Model-based Policy Optimization with Unsupervised Model Adaptation","created":"2020-10-19","cited_by_count":16},{"id":"2010.05545","title":"Local Search for Policy Iteration in Continuous Control","created":"2020-10-12","cited_by_count":9}],"next_cursor":null}