{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1703.00956","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","created":"2017-03-02","cited_by_count":110},{"id":"1810.01257","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","created":"2018-10-02","cited_by_count":110},{"id":"2206.02574","title":"On the duality between contrastive and non-contrastive self-supervised learning","created":"2022-06-03","cited_by_count":108},{"id":"2004.14646","title":"Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning","created":"2020-04-30","cited_by_count":102},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","cited_by_count":86},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57},{"id":"1901.11530","title":"A Geometric Perspective on Optimal Representations for Reinforcement Learning","created":"2019-01-31","cited_by_count":54},{"id":"1602.07764","title":"Reinforcement Learning of POMDPs using Spectral Methods","created":"2016-02-25","cited_by_count":52},{"id":"1909.01387","title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems","created":"2019-09-03","cited_by_count":45},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43},{"id":"2010.00554","title":"EigenGame: PCA as a Nash Equilibrium","created":"2020-10-01","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":"2007.05520","title":"Representations for Stable Off-Policy Reinforcement Learning","created":"2020-07-10","cited_by_count":31},{"id":"2205.00165","title":"NeuralEF: Deconstructing Kernels by Deep Neural Networks","created":"2022-04-30","cited_by_count":27},{"id":"2107.05545","title":"Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing","created":"2021-07-12","cited_by_count":23},{"id":"2205.13476","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","created":"2022-05-26","cited_by_count":16},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14},{"id":"1902.07685","title":"World Discovery Models","created":"2019-02-20","cited_by_count":10},{"id":"2203.11369","title":"Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL","created":"2022-03-21","cited_by_count":7},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7},{"id":"1712.04065","title":"The Eigenoption-Critic Framework","created":"2017-12-11","cited_by_count":3}],"next_cursor":null}