{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"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":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2010.15277","title":"Class-incremental learning: survey and performance evaluation on image classification","created":"2020-10-28","cited_by_count":449},{"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":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"2006.07869","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","created":"2020-06-14","cited_by_count":212},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"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":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56},{"id":"2110.14300","title":"Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks","created":"2021-10-27","cited_by_count":54},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49},{"id":"2009.11997","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","created":"2020-09-25","cited_by_count":44},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"1902.00255","title":"Policy Consolidation for Continual Reinforcement Learning","created":"2019-02-01","cited_by_count":39},{"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":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36},{"id":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","cited_by_count":32},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28},{"id":"2006.00587","title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization","created":"2020-05-31","cited_by_count":26},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25},{"id":"2001.05411","title":"Lipschitz Lifelong Reinforcement Learning","created":"2020-01-15","cited_by_count":23},{"id":"2007.14196","title":"Lifelong Incremental Reinforcement Learning with Online Bayesian Inference","created":"2020-07-28","cited_by_count":23},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","cited_by_count":21},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17},{"id":"2211.15944","title":"The Effectiveness of World Models for Continual Reinforcement Learning","created":"2022-11-29","cited_by_count":17},{"id":"1911.04094","title":"SMIX($\\lambda$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning","created":"2019-11-11","cited_by_count":15},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12},{"id":"2109.12508","title":"LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates","created":"2021-09-26","cited_by_count":9},{"id":"2203.14477","title":"UNMAS: Multi-Agent Reinforcement Learning for Unshaped Cooperative Scenarios","created":"2022-03-28","cited_by_count":9},{"id":"2108.12988","title":"Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning","created":"2021-08-30","cited_by_count":6}],"next_cursor":null}