{"list":"other","total":101,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"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":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"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":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"1710.08005","title":"Smart \"Predict, then Optimize\"","created":"2017-10-22","cited_by_count":339},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"1809.05504","title":"Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization","created":"2018-09-14","cited_by_count":227},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"1810.13400","title":"Differentiable MPC for End-to-end Planning and Control","created":"2018-10-31","cited_by_count":189},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"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":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"2001.07203","title":"Active inference on discrete state-spaces: a synthesis","created":"2020-01-20","cited_by_count":92},{"id":"2010.11876","title":"Error Bounds of Imitating Policies and Environments","created":"2020-10-22","cited_by_count":90},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90},{"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":"1909.11639","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","created":"2019-09-25","cited_by_count":72},{"id":"2006.04176","title":"Deep active inference agents using Monte-Carlo methods","created":"2020-06-07","cited_by_count":72},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"2010.08843","title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","created":"2020-10-17","cited_by_count":70},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66},{"id":"1907.03876","title":"Deep Active Inference as Variational Policy Gradients","created":"2019-07-08","cited_by_count":53},{"id":"1703.06692","title":"QMDP-Net: Deep Learning for Planning under Partial Observability","created":"2017-03-20","cited_by_count":51},{"id":"2008.12775","title":"On the model-based stochastic value gradient for continuous reinforcement learning","created":"2020-08-28","cited_by_count":47},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","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":"1807.08706","title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","created":"2018-07-23","cited_by_count":44},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44},{"id":"1612.06018","title":"Self-Correcting Models for Model-Based Reinforcement Learning","created":"2016-12-19","cited_by_count":43},{"id":"2006.12964","title":"On the Relationship Between Active Inference and Control as Inference","created":"2020-06-23","cited_by_count":42},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42},{"id":"2004.08128","title":"Whence the Expected Free Energy?","created":"2020-04-17","cited_by_count":40},{"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":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33},{"id":"1907.13122","title":"Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization","created":"2019-07-29","cited_by_count":32},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32},{"id":"1712.00287","title":"Faithful Inversion of Generative Models for Effective Amortized Inference","created":"2017-12-01","cited_by_count":29},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","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":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28},{"id":"1909.12830","title":"The Differentiable Cross-Entropy Method","created":"2019-09-27","cited_by_count":27},{"id":"1804.10689","title":"Decoupling Dynamics and Reward for Transfer Learning","created":"2018-04-27","cited_by_count":23},{"id":"2003.00030","title":"Policy-Aware Model Learning for Policy Gradient Methods","created":"2020-02-28","cited_by_count":23},{"id":"2012.09156","title":"Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning","created":"2020-12-16","cited_by_count":21},{"id":"1703.09260","title":"Goal-Driven Dynamics Learning via Bayesian Optimization","created":"2017-03-27","cited_by_count":19},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"1909.01506","title":"Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control","created":"2019-09-04","cited_by_count":18},{"id":"2204.13319","title":"Control-Aware Prediction Objectives for Autonomous Driving","created":"2022-04-28","cited_by_count":18},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17},{"id":"1706.09597","title":"Path Integral Networks: End-to-End Differentiable Optimal Control","created":"2017-06-29","cited_by_count":16},{"id":"2010.13685","title":"Forethought and Hindsight in Credit Assignment","created":"2020-10-26","cited_by_count":16},{"id":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12},{"id":"2112.03899","title":"Information is Power: Intrinsic Control via Information Capture","created":"2021-12-07","cited_by_count":11},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10},{"id":"2010.00262","title":"Active Inference or Control as Inference? A Unifying View","created":"2020-10-01","cited_by_count":9},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9},{"id":"2006.05443","title":"Variational Model-based Policy Optimization","created":"2020-06-09","cited_by_count":7},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6},{"id":"2302.02529","title":"Learning Control-Oriented Dynamical Structure from Data","created":"2023-02-06","cited_by_count":5},{"id":"2103.12999","title":"Discriminator Augmented Model-Based Reinforcement Learning","created":"2021-03-24","cited_by_count":2}],"next_cursor":"100"}