{"list":"other","total":61,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"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":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"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":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"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":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"1606.02396","title":"Deep Successor Reinforcement Learning","created":"2016-06-08","cited_by_count":72},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2006.12484","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","created":"2020-06-22","cited_by_count":66},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54},{"id":"1602.07764","title":"Reinforcement Learning of POMDPs using Spectral Methods","created":"2016-02-25","cited_by_count":52},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52},{"id":"1804.06309","title":"On Improving Deep Reinforcement Learning for POMDPs","created":"2018-04-17","cited_by_count":50},{"id":"1401.3436","title":"Online Planning Algorithms for POMDPs","created":"2014-01-15","cited_by_count":45},{"id":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","cited_by_count":44},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43},{"id":"1811.06407","title":"Neural Predictive Belief Representations","created":"2018-11-15","cited_by_count":40},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39},{"id":"1605.08062","title":"A PAC RL Algorithm for Episodic POMDPs","created":"2016-05-25","cited_by_count":37},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30},{"id":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26},{"id":"1906.09510","title":"Learning Belief Representations for Imitation Learning in POMDPs","created":"2019-06-22","cited_by_count":24},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24},{"id":"1811.02619","title":"State Aggregation Learning from Markov Transition Data","created":"2018-11-06","cited_by_count":20},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15},{"id":"1602.04875","title":"POMDP-lite for Robust Robot Planning under Uncertainty","created":"2016-02-16","cited_by_count":12},{"id":"2306.12356","title":"Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP","created":"2023-06-21","cited_by_count":8},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6},{"id":"2104.10986","title":"Reinforcement Learning using Guided Observability","created":"2021-04-22","cited_by_count":3}],"next_cursor":null}