{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"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":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"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":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"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":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","cited_by_count":125},{"id":"1812.09755","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","created":"2018-12-23","cited_by_count":121},{"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":"2011.02669","title":"Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping","created":"2020-11-05","cited_by_count":114},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"1810.01257","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","created":"2018-10-02","cited_by_count":110},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98},{"id":"2011.00583","title":"Game-Theoretic Multiagent Reinforcement Learning","created":"2020-11-01","cited_by_count":94},{"id":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"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":"1911.06992","title":"Learning Efficient Multi-agent Communication: An Information Bottleneck Approach","created":"2019-11-16","cited_by_count":61},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"2006.16232","title":"Learning Robot Skills with Temporal Variational Inference","created":"2020-06-29","cited_by_count":54},{"id":"2004.11812","title":"Self-Paced Deep Reinforcement Learning","created":"2020-04-24","cited_by_count":50},{"id":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"1912.03558","title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery","created":"2019-12-07","cited_by_count":43},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39},{"id":"2006.04222","title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","created":"2020-06-07","cited_by_count":38},{"id":"1909.02790","title":"From Few to More: Large-scale Dynamic Multiagent Curriculum Learning","created":"2019-09-06","cited_by_count":36},{"id":"1812.00285","title":"Learning Curriculum Policies for Reinforcement Learning","created":"2018-12-01","cited_by_count":35},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26},{"id":"1811.09083","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","created":"2018-11-22","cited_by_count":24},{"id":"2110.04507","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","created":"2021-10-09","cited_by_count":18},{"id":"1809.09095","title":"On Reinforcement Learning for Full-length Game of StarCraft","created":"2018-09-23","cited_by_count":16},{"id":"2110.14241","title":"Dynamic population-based meta-learning for multi-agent communication with natural language","created":"2021-10-27","cited_by_count":10},{"id":"1906.01470","title":"Options as responses: Grounding behavioural hierarchies in multi-agent RL","created":"2019-06-04","cited_by_count":7},{"id":"2011.08463","title":"Meta Automatic Curriculum Learning","created":"2020-11-16","cited_by_count":6},{"id":"2110.08169","title":"Containerized Distributed Value-Based Multi-Agent Reinforcement Learning","created":"2021-10-15","cited_by_count":1}],"next_cursor":null}