{"list":"other","total":64,"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":"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":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"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":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"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":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"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":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1906.08291","title":"Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks","created":"2019-06-19","cited_by_count":199},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"1809.03531","title":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","created":"2018-09-10","cited_by_count":90},{"id":"1709.10082","title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","created":"2017-09-28","cited_by_count":83},{"id":"2010.01367","title":"EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding","created":"2020-10-03","cited_by_count":68},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68},{"id":"2010.08184","title":"PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong","created":"2020-10-16","cited_by_count":63},{"id":"1901.11282","title":"Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding","created":"2019-01-31","cited_by_count":57},{"id":"1910.11689","title":"Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning","created":"2019-10-24","cited_by_count":49},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42},{"id":"1809.04506","title":"Combined Reinforcement Learning via Abstract Representations","created":"2018-09-12","cited_by_count":37},{"id":"2005.05420","title":"Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning","created":"2020-05-11","cited_by_count":37},{"id":"2303.00605","title":"SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding","created":"2023-03-01","cited_by_count":37},{"id":"2301.05832","title":"World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges","created":"2023-01-14","cited_by_count":36},{"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":"2007.15724","title":"MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments","created":"2020-07-30","cited_by_count":26},{"id":"1905.04100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","created":"2019-02-19","cited_by_count":24},{"id":"2005.05441","title":"Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments","created":"2020-05-11","cited_by_count":22},{"id":"2001.06627","title":"Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning","created":"2020-01-18","cited_by_count":21},{"id":"2103.07116","title":"Pairwise Symmetry Reasoning for Multi-Agent Path Finding Search","created":"2021-03-12","cited_by_count":21},{"id":"2202.03634","title":"Multi-Agent Path Finding with Prioritized Communication Learning","created":"2022-02-08","cited_by_count":18},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17},{"id":"2305.06436","title":"Multi-Robot Coordination and Layout Design for Automated Warehousing","created":"2023-05-10","cited_by_count":17},{"id":"1509.01549","title":"Giraffe: Using Deep Reinforcement Learning to Play Chess","created":"2015-09-04","cited_by_count":12},{"id":"2103.16511","title":"Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World","created":"2021-03-30","cited_by_count":10},{"id":"2207.00576","title":"Conflict-based Search for Multi-Robot Motion Planning with Kinodynamic Constraints","created":"2022-07-01","cited_by_count":10},{"id":"2307.03860","title":"Reinforcement and Deep Reinforcement Learning-based Solutions for Machine Maintenance Planning, Scheduling Policies, and Optimization","created":"2023-07-07","cited_by_count":8},{"id":"2012.06005","title":"Learning to Resolve Conflicts for Multi-Agent Path Finding with Conflict-Based Search","created":"2020-12-10","cited_by_count":7},{"id":"2206.11319","title":"Graph-Based Multi-Robot Path Finding and Planning","created":"2022-06-22","cited_by_count":7},{"id":"2206.10944","title":"POGEMA: Partially Observable Grid Environment for Multiple Agents","created":"2022-06-22","cited_by_count":6},{"id":"2105.07132","title":"Offline Time-Independent Multi-Agent Path Planning","created":"2021-05-15","cited_by_count":5},{"id":"2006.15009","title":"A Unifying Framework for Reinforcement Learning and Planning","created":"2020-06-26","cited_by_count":4},{"id":"2107.00246","title":"Distributed Multi-agent Navigation Based on Reciprocal Collision Avoidance and Locally Confined Multi-agent Path Finding","created":"2021-07-01","cited_by_count":4},{"id":"1912.09503","title":"Multi-Robot Path Planning Via Genetic Programming","created":"2019-12-19","cited_by_count":1},{"id":"2201.09746","title":"Reinforcement Learning Textbook","created":"2022-01-19","cited_by_count":1}],"next_cursor":null}