{"list":"other","total":74,"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"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":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"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":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1910.07483","title":"MAVEN: Multi-Agent Variational Exploration","created":"2019-10-16","cited_by_count":185},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"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":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"1809.03531","title":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","created":"2018-09-10","cited_by_count":90},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"1707.06600","title":"A multi-agent reinforcement learning model of common-pool resource appropriation","created":"2017-07-20","cited_by_count":69},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"1906.02403","title":"Ease-of-Teaching and Language Structure from Emergent Communication","created":"2019-06-06","cited_by_count":65},{"id":"2010.08184","title":"PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong","created":"2020-10-16","cited_by_count":63},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"1909.02682","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","created":"2019-09-06","cited_by_count":46},{"id":"1903.00784","title":"Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents","created":"2019-03-02","cited_by_count":44},{"id":"1906.01202","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","created":"2019-06-04","cited_by_count":44},{"id":"1910.04700","title":"Assistive Gym: A Physics Simulation Framework for Assistive Robotics","created":"2019-10-10","cited_by_count":44},{"id":"1707.04402","title":"Lenient Multi-Agent Deep Reinforcement Learning","created":"2017-07-14","cited_by_count":35},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32},{"id":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32},{"id":"1809.07124","title":"Pommerman: A Multi-Agent Playground","created":"2018-09-19","cited_by_count":30},{"id":"2008.02616","title":"The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning","created":"2020-08-06","cited_by_count":28},{"id":"1912.03821","title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","created":"2019-12-09","cited_by_count":23},{"id":"2106.02067","title":"Learning to Draw: Emergent Communication through Sketching","created":"2021-06-03","cited_by_count":23},{"id":"1811.07029","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","created":"2018-11-13","cited_by_count":20},{"id":"1910.12639","title":"MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding","created":"2019-10-25","cited_by_count":20},{"id":"1901.03887","title":"Improving Coordination in Small-Scale Multi-Agent Deep Reinforcement Learning through Memory-driven Communication","created":"2019-01-12","cited_by_count":18},{"id":"2007.14297","title":"Cooperative Internet of UAVs: Distributed Trajectory Design by Multi-agent Deep Reinforcement Learning","created":"2020-07-28","cited_by_count":18},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18},{"id":"2202.03634","title":"Multi-Agent Path Finding with Prioritized Communication Learning","created":"2022-02-08","cited_by_count":18},{"id":"2112.09012","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","created":"2021-12-16","cited_by_count":13},{"id":"1712.07305","title":"Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning","created":"2017-12-20","cited_by_count":12},{"id":"1909.08776","title":"Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net","created":"2019-09-19","cited_by_count":12},{"id":"2004.00470","title":"Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication","created":"2020-04-01","cited_by_count":12},{"id":"2105.06593","title":"Emergent Prosociality in Multi-Agent Games Through Gifting","created":"2021-05-13","cited_by_count":12},{"id":"1706.03235","title":"ACCNet: Actor-Coordinator-Critic Net for \"Learning-to-Communicate\" with Deep Multi-agent Reinforcement Learning","created":"2017-06-10","cited_by_count":8},{"id":"2003.09540","title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation","created":"2020-03-21","cited_by_count":7},{"id":"2201.11994","title":"FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems","created":"2022-01-28","cited_by_count":7},{"id":"2112.06594","title":"Multi-agent Soft Actor-Critic Based Hybrid Motion Planner for Mobile Robots","created":"2021-12-13","cited_by_count":5},{"id":"2112.12740","title":"Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling","created":"2021-12-23","cited_by_count":5},{"id":"2006.08152","title":"ForMIC: Foraging via Multiagent RL with Implicit Communication","created":"2020-06-15","cited_by_count":4}],"next_cursor":null}