{"list":"other","total":53,"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"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":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"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":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"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":"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":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","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":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"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":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"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":"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":"1804.06459","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","created":"2018-04-17","cited_by_count":102},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"2006.09641","title":"Automatic Curriculum Learning through Value Disagreement","created":"2020-06-17","cited_by_count":87},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1909.04607","title":"Discovery of Useful Questions as Auxiliary Tasks","created":"2019-09-10","cited_by_count":45},{"id":"1711.06006","title":"Hindsight policy gradients","created":"2017-11-16","cited_by_count":37},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24},{"id":"1806.09605","title":"Many-Goals Reinforcement Learning","created":"2018-06-22","cited_by_count":22},{"id":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11}],"next_cursor":null}