{"list":"other","total":57,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1906.01563","title":"Hamiltonian Neural Networks","created":"2019-06-04","cited_by_count":712},{"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":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2003.04630","title":"Lagrangian Neural Networks","created":"2020-03-10","cited_by_count":398},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2006.16908","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","created":"2020-06-30","cited_by_count":142},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"1911.09291","title":"Scalable methods for computing state similarity in deterministic Markov Decision Processes","created":"2019-11-21","cited_by_count":133},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"1901.08933","title":"Self-Supervised Generalisation with Meta Auxiliary Learning","created":"2019-01-25","cited_by_count":88},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85},{"id":"2203.04439","title":"$\\mathrm{SO}(2)$-Equivariant Reinforcement Learning","created":"2022-03-08","cited_by_count":84},{"id":"1902.00183","title":"Learning Action Representations for Reinforcement Learning","created":"2019-02-01","cited_by_count":75},{"id":"1701.04113","title":"Near Optimal Behavior via Approximate State Abstraction","created":"2017-01-15","cited_by_count":66},{"id":"2002.11963","title":"Plannable Approximations to MDP Homomorphisms: Equivariance under Actions","created":"2020-02-27","cited_by_count":61},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57},{"id":"2204.11371","title":"Learning Symmetric Embeddings for Equivariant World Models","created":"2022-04-24","cited_by_count":54},{"id":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","cited_by_count":49},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43},{"id":"1904.00243","title":"Symmetry-Based Disentangled Representation Learning requires Interaction with Environments","created":"2019-03-30","cited_by_count":35},{"id":"1908.09357","title":"Dynamics-aware Embeddings","created":"2019-08-25","cited_by_count":34},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33},{"id":"1902.01119","title":"The Natural Language of Actions","created":"2019-02-04","cited_by_count":28},{"id":"2110.04495","title":"Multi-Agent MDP Homomorphic Networks","created":"2021-10-09","cited_by_count":25},{"id":"2011.07537","title":"Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking","created":"2020-11-15","cited_by_count":19},{"id":"1705.07269","title":"Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning","created":"2017-05-20","cited_by_count":15},{"id":"1706.02999","title":"Symmetry Learning for Function Approximation in Reinforcement Learning","created":"2017-06-09","cited_by_count":14},{"id":"1811.12929","title":"Online Abstraction with MDP Homomorphisms for Deep Learning","created":"2018-11-30","cited_by_count":13},{"id":"2002.06991","title":"Learning Group Structure and Disentangled Representations of Dynamical Environments","created":"2020-02-17","cited_by_count":13},{"id":"1708.01289","title":"Independently Controllable Factors","created":"2017-08-03","cited_by_count":12},{"id":"2003.04300","title":"Learning Discrete State Abstractions With Deep Variational Inference","created":"2020-03-09","cited_by_count":10},{"id":"2111.05986","title":"SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision","created":"2021-11-10","cited_by_count":5}],"next_cursor":null}