{"list":"other","total":84,"rows":[{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","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":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"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":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"1605.02097","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","created":"2016-05-06","cited_by_count":179},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"1607.00215","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","created":"2016-07-01","cited_by_count":117},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"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":"1810.02274","title":"Episodic Curiosity through Reachability","created":"2018-10-04","cited_by_count":109},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","cited_by_count":86},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"1812.03381","title":"Learning Montezuma's Revenge from a Single Demonstration","created":"2018-12-08","cited_by_count":80},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"id":"1812.07544","title":"Information-Directed Exploration for Deep Reinforcement Learning","created":"2018-12-18","cited_by_count":52},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"1909.01387","title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems","created":"2019-09-03","cited_by_count":45},{"id":"2007.03669","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","created":"2020-07-07","cited_by_count":43},{"id":"1703.01260","title":"EX2: Exploration with Exemplar Models for Deep Reinforcement Learning","created":"2017-03-03","cited_by_count":42},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"1402.0560","title":"Safe Exploration of State and Action Spaces in Reinforcement Learning","created":"2014-02-04","cited_by_count":38},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"1805.10309","title":"Learning Self-Imitating Diverse Policies","created":"2018-05-25","cited_by_count":29},{"id":"1902.08039","title":"Curiosity-Driven Experience Prioritization via Density Estimation","created":"2019-02-20","cited_by_count":27},{"id":"1811.01483","title":"Contingency-Aware Exploration in Reinforcement Learning","created":"2018-11-05","cited_by_count":26},{"id":"1803.00781","title":"Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration","created":"2018-03-02","cited_by_count":23},{"id":"2002.03218","title":"Conservative Exploration in Reinforcement Learning","created":"2020-02-08","cited_by_count":20},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"1911.00617","title":"Explicit Explore-Exploit Algorithms in Continuous State Spaces","created":"2019-11-01","cited_by_count":19},{"id":"1805.01907","title":"Exploration by Distributional Reinforcement Learning","created":"2018-05-04","cited_by_count":13},{"id":"1806.00553","title":"Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems","created":"2018-06-01","cited_by_count":12},{"id":"1807.02397","title":"Quality Diversity Through Surprise","created":"2018-07-06","cited_by_count":12},{"id":"2004.11667","title":"PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning","created":"2020-04-24","cited_by_count":12},{"id":"1906.07805","title":"Directed Exploration for Reinforcement Learning","created":"2019-06-18","cited_by_count":9},{"id":"2008.04388","title":"GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning","created":"2020-08-10","cited_by_count":9},{"id":"1509.06824","title":"Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration","created":"2015-09-23","cited_by_count":8},{"id":"1603.04119","title":"Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains","created":"2016-03-14","cited_by_count":8},{"id":"1909.04307","title":"Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning","created":"2019-09-10","cited_by_count":7},{"id":"1802.02274","title":"A Critical Investigation of Deep Reinforcement Learning for Navigation","created":"2018-02-07","cited_by_count":6},{"id":"1801.07440","title":"Curiosity-driven reinforcement learning with homeostatic regulation","created":"2018-01-23","cited_by_count":4},{"id":"1901.02478","title":"Visual novelty, curiosity, and intrinsic reward in machine learning and the brain","created":"2019-01-08","cited_by_count":4},{"id":"1907.11788","title":"On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman","created":"2019-07-26","cited_by_count":4},{"id":"2007.05896","title":"Learning Abstract Models for Strategic Exploration and Fast Reward Transfer","created":"2020-07-12","cited_by_count":4},{"id":"2011.08027","title":"ACDER: Augmented Curiosity-Driven Experience Replay","created":"2020-11-16","cited_by_count":4},{"id":"2201.11685","title":"Generative Adversarial Exploration for Reinforcement Learning","created":"2022-01-27","cited_by_count":3},{"id":"1805.11324","title":"Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning","created":"2018-05-29","cited_by_count":2},{"id":"1906.06890","title":"Learning-Driven Exploration for Reinforcement Learning","created":"2019-06-17","cited_by_count":2}],"next_cursor":null}