{"list":"other","total":56,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"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":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","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":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"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":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"1803.08884","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","created":"2018-03-23","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":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"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":"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":"2011.12692","title":"Towards Playing Full MOBA Games with Deep Reinforcement Learning","created":"2020-11-25","cited_by_count":78},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"1903.05168","title":"On the Pitfalls of Measuring Emergent Communication","created":"2019-03-12","cited_by_count":71},{"id":"1707.06600","title":"A multi-agent reinforcement learning model of common-pool resource appropriation","created":"2017-07-20","cited_by_count":69},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"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":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"2002.02325","title":"Social diversity and social preferences in mixed-motive reinforcement learning","created":"2020-02-06","cited_by_count":49},{"id":"1707.01068","title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","created":"2017-07-04","cited_by_count":48},{"id":"1709.02865","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","created":"2017-09-08","cited_by_count":47},{"id":"1806.02643","title":"Re-evaluating Evaluation","created":"2018-06-07","cited_by_count":47},{"id":"1910.13406","title":"Generalization of Reinforcement Learners with Working and Episodic Memory","created":"2019-10-29","cited_by_count":36},{"id":"1811.06032","title":"Natural Environment Benchmarks for Reinforcement Learning","created":"2018-11-14","cited_by_count":32},{"id":"2003.11778","title":"Too many cooks: Bayesian inference for coordinating multi-agent collaboration","created":"2020-03-26","cited_by_count":29},{"id":"1806.02448","title":"Deep Reinforcement Learning for General Video Game AI","created":"2018-06-06","cited_by_count":25},{"id":"1812.07019","title":"Malthusian Reinforcement Learning","created":"2018-12-17","cited_by_count":14},{"id":"1901.08129","title":"The Multi-Agent Reinforcement Learning in Malm\\\"O (MARL\\\"O) Competition","created":"2019-01-23","cited_by_count":14},{"id":"2010.09054","title":"Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences","created":"2020-10-18","cited_by_count":13},{"id":"2011.07027","title":"DeepMind Lab2D","created":"2020-11-13","cited_by_count":13},{"id":"1905.08085","title":"Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence","created":"2019-05-17","cited_by_count":9}],"next_cursor":null}