{"list":"other","total":90,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"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":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"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":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"2006.07869","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","created":"2020-06-14","cited_by_count":212},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126},{"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":"1702.08887","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","created":"2017-02-28","cited_by_count":117},{"id":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"1803.08884","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","created":"2018-03-23","cited_by_count":106},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99},{"id":"1910.00091","title":"Deep Coordination Graphs","created":"2019-09-27","cited_by_count":98},{"id":"2308.11339","title":"ProAgent: Building Proactive Cooperative Agents with Large Language Models","created":"2023-08-22","cited_by_count":98},{"id":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"id":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"2002.03939","title":"Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":81},{"id":"1907.05707","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","created":"2019-07-11","cited_by_count":73},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70},{"id":"1707.06600","title":"A multi-agent reinforcement learning model of common-pool resource appropriation","created":"2017-07-20","cited_by_count":69},{"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":"2006.06051","title":"Learning to Incentivize Other Learning Agents","created":"2020-06-10","cited_by_count":57},{"id":"1706.06122","title":"VAIN: Attentional Multi-agent Predictive Modeling","created":"2017-06-19","cited_by_count":53},{"id":"2004.01339","title":"Multi-agent Reinforcement Learning for Networked System Control","created":"2020-04-03","cited_by_count":53},{"id":"2006.06626","title":"Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward","created":"2020-06-11","cited_by_count":50},{"id":"1811.08469","title":"Stable Opponent Shaping in Differentiable Games","created":"2018-11-20","cited_by_count":49},{"id":"2002.02325","title":"Social diversity and social preferences in mixed-motive reinforcement learning","created":"2020-02-06","cited_by_count":49},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","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":"2205.01447","title":"Model-Free Opponent Shaping","created":"2022-05-03","cited_by_count":44},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40},{"id":"2006.10412","title":"Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning","created":"2020-06-18","cited_by_count":37},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34},{"id":"1811.05931","title":"Evolving intrinsic motivations for altruistic behavior","created":"2018-11-14","cited_by_count":30},{"id":"2302.04831","title":"Cooperative Open-ended Learning Framework for Zero-shot Coordination","created":"2023-02-09","cited_by_count":30},{"id":"2006.00587","title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization","created":"2020-05-31","cited_by_count":26},{"id":"2105.15013","title":"SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning","created":"2021-05-31","cited_by_count":26},{"id":"2301.06387","title":"PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination","created":"2023-01-16","cited_by_count":25},{"id":"1903.08082","title":"Learning Reciprocity in Complex Sequential Social Dilemmas","created":"2019-03-19","cited_by_count":24},{"id":"2106.09012","title":"A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings","created":"2021-06-16","cited_by_count":24},{"id":"1912.03821","title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","created":"2019-12-09","cited_by_count":23},{"id":"2011.05373","title":"Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences","created":"2020-11-10","cited_by_count":21},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19},{"id":"2010.15896","title":"Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations","created":"2020-10-29","cited_by_count":18},{"id":"2010.00575","title":"D3C: Reducing the Price of Anarchy in Multi-Agent Learning","created":"2020-10-01","cited_by_count":16},{"id":"1812.07019","title":"Malthusian Reinforcement Learning","created":"2018-12-17","cited_by_count":14},{"id":"2108.02755","title":"The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning","created":"2021-08-05","cited_by_count":14},{"id":"2004.02780","title":"Networked Multi-Agent Reinforcement Learning with Emergent Communication","created":"2020-04-06","cited_by_count":13},{"id":"2010.09054","title":"Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences","created":"2020-10-18","cited_by_count":13},{"id":"2102.07523","title":"Cooperation and Reputation Dynamics with Reinforcement Learning","created":"2021-02-15","cited_by_count":13},{"id":"2105.06593","title":"Emergent Prosociality in Multi-Agent Games Through Gifting","created":"2021-05-13","cited_by_count":12},{"id":"1606.00753","title":"Social learning strategies modify the effect of network structure on group performance","created":"2016-06-02","cited_by_count":10},{"id":"2003.00799","title":"Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games","created":"2020-02-27","cited_by_count":9},{"id":"2103.04982","title":"A multi-agent reinforcement learning model of reputation and cooperation in human groups","created":"2021-03-08","cited_by_count":6},{"id":"2210.17540","title":"Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning","created":"2022-10-31","cited_by_count":6},{"id":"2310.12928","title":"Resolving social dilemmas with minimal reward transfer","created":"2023-10-19","cited_by_count":6},{"id":"2304.07520","title":"STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning","created":"2023-04-15","cited_by_count":5},{"id":"2207.05886","title":"Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior","created":"2022-07-12","cited_by_count":4},{"id":"2208.10469","title":"Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL","created":"2022-08-22","cited_by_count":4},{"id":"1906.09831","title":"Foolproof Cooperative Learning","created":"2019-06-24","cited_by_count":3},{"id":"2301.07416","title":"Learning to Participate through Trading of Reward Shares","created":"2023-01-18","cited_by_count":2},{"id":"2302.01180","title":"Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition","created":"2023-02-02","cited_by_count":2},{"id":"2305.00768","title":"Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas","created":"2023-05-01","cited_by_count":2}],"next_cursor":null}