{"list":"other","total":65,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"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":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","created":"2019-01-07","cited_by_count":192},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"1702.00539","title":"Procedural Content Generation via Machine Learning (PCGML)","created":"2017-02-02","cited_by_count":137},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","cited_by_count":91},{"id":"2001.09212","title":"PCGRL: Procedural Content Generation via Reinforcement Learning","created":"2020-01-24","cited_by_count":90},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"2006.09641","title":"Automatic Curriculum Learning through Value Disagreement","created":"2020-06-17","cited_by_count":87},{"id":"2010.04548","title":"Deep Learning for Procedural Content Generation","created":"2020-10-09","cited_by_count":73},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"1707.02267","title":"Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task","created":"2017-07-07","cited_by_count":66},{"id":"1911.13071","title":"Increasing Generality in Machine Learning through Procedural Content Generation","created":"2019-11-29","cited_by_count":59},{"id":"1711.05726","title":"Markov Decision Processes with Continuous Side Information","created":"2017-11-15","cited_by_count":56},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"1804.05464","title":"On Gradient-Based Learning in Continuous Games","created":"2018-04-16","cited_by_count":48},{"id":"1912.02288","title":"Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2019-12-04","cited_by_count":48},{"id":"1802.10363","title":"General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms","created":"2018-02-28","cited_by_count":45},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42},{"id":"2105.02993","title":"Learning Controllable Content Generators","created":"2021-05-06","cited_by_count":40},{"id":"2106.10853","title":"On the Importance of Environments in Human-Robot Coordination","created":"2021-06-21","cited_by_count":37},{"id":"2109.05489","title":"Illuminating Diverse Neural Cellular Automata for Level Generation","created":"2021-09-12","cited_by_count":35},{"id":"1910.02826","title":"Self-Paced Contextual Reinforcement Learning","created":"2019-10-07","cited_by_count":26},{"id":"2106.05110","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","created":"2021-06-09","cited_by_count":25},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"1610.01685","title":"Supervision via Competition: Robot Adversaries for Learning Tasks","created":"2016-10-05","cited_by_count":16},{"id":"2007.08497","title":"Co-generation of game levels and game-playing agents","created":"2020-07-16","cited_by_count":14},{"id":"2103.01991","title":"Adversarial Environment Generation for Learning to Navigate the Web","created":"2021-03-02","cited_by_count":13},{"id":"1907.06077","title":"Evolvability ES: Scalable and Direct Optimization of Evolvability","created":"2019-07-13","cited_by_count":7},{"id":"2002.07911","title":"Generating Automatic Curricula via Self-Supervised Active Domain Randomization","created":"2020-02-18","cited_by_count":7}],"next_cursor":null}