{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"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":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"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":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1910.07483","title":"MAVEN: Multi-Agent Variational Exploration","created":"2019-10-16","cited_by_count":185},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"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":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"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":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"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":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1909.12238","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","created":"2019-09-26","cited_by_count":85},{"id":"1902.02186","title":"Distilling Policy Distillation","created":"2019-02-06","cited_by_count":84},{"id":"1803.03835","title":"Kickstarting Deep Reinforcement Learning","created":"2018-03-10","cited_by_count":81},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"2004.09468","title":"Real World Games Look Like Spinning Tops","created":"2020-04-20","cited_by_count":66},{"id":"1903.00742","title":"Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research","created":"2019-03-02","cited_by_count":61},{"id":"2001.01394","title":"A Boolean Task Algebra for Reinforcement Learning","created":"2020-01-06","cited_by_count":48},{"id":"1806.02643","title":"Re-evaluating Evaluation","created":"2018-06-07","cited_by_count":47},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"2012.04751","title":"EvoCraft: A New Challenge for Open-Endedness","created":"2020-12-08","cited_by_count":23},{"id":"2106.09435","title":"Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers","created":"2021-06-17","cited_by_count":21},{"id":"2004.01703","title":"CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation","created":"2020-04-03","cited_by_count":19},{"id":"2006.07043","title":"Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL","created":"2020-06-12","cited_by_count":12},{"id":"2107.06327","title":"Contextual Games: Multi-Agent Learning with Side Information","created":"2021-07-13","cited_by_count":11}],"next_cursor":null}