{"list":"other","total":82,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"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":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"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":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"1906.05030","title":"Fast Task Inference with Variational Intrinsic Successor Features","created":"2019-06-12","cited_by_count":133},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"1704.03012","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","created":"2017-04-10","cited_by_count":124},{"id":"1807.10299","title":"Variational Option Discovery Algorithms","created":"2018-07-26","cited_by_count":122},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","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":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","cited_by_count":86},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"1903.11780","title":"Wasserstein Dependency Measure for Representation Learning","created":"2019-03-28","cited_by_count":69},{"id":"1907.08225","title":"Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery","created":"2019-07-18","cited_by_count":68},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58},{"id":"1806.02813","title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","created":"2018-06-07","cited_by_count":52},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49},{"id":"1703.01260","title":"EX2: Exploration with Exemplar Models for Deep Reinforcement Learning","created":"2017-03-03","cited_by_count":42},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38},{"id":"2012.07827","title":"Relative Variational Intrinsic Control","created":"2020-12-14","cited_by_count":34},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28},{"id":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22},{"id":"2110.07940","title":"Wasserstein Unsupervised Reinforcement Learning","created":"2021-10-15","cited_by_count":22},{"id":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21},{"id":"1905.10681","title":"Composing Task-Agnostic Policies with Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":20},{"id":"2110.14457","title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching","created":"2021-10-27","cited_by_count":19},{"id":"1901.00943","title":"Self-supervised Learning of Image Embedding for Continuous Control","created":"2019-01-03","cited_by_count":16},{"id":"2302.00270","title":"Internally Rewarded Reinforcement Learning","created":"2023-02-01","cited_by_count":14},{"id":"2112.03899","title":"Information is Power: Intrinsic Control via Information Capture","created":"2021-12-07","cited_by_count":11},{"id":"2203.11176","title":"One After Another: Learning Incremental Skills for a Changing World","created":"2022-03-21","cited_by_count":10},{"id":"2210.06702","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","created":"2022-10-13","cited_by_count":9},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8}],"next_cursor":null}