{"list":"other","total":53,"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"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":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"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":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"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":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"2202.08449","title":"V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving","created":"2022-02-17","cited_by_count":157},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"2007.12322","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","created":"2020-07-24","cited_by_count":98},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"2002.03939","title":"Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":81},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49},{"id":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33},{"id":"2112.02845","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","created":"2021-12-06","cited_by_count":32},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17},{"id":"2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","created":"2021-07-03","cited_by_count":16},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12},{"id":"2402.05643","title":"Improving Token-Based World Models with Parallel Observation Prediction","created":"2024-02-08","cited_by_count":11},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","cited_by_count":9},{"id":"2404.03869","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","created":"2024-04-05","cited_by_count":6},{"id":"2111.14177","title":"Evaluating Generalization and Transfer Capacity of Multi-Agent Reinforcement Learning Across Variable Number of Agents","created":"2021-11-28","cited_by_count":3},{"id":"2403.15916","title":"Multi-agent transformer-accelerated RL for satisfaction of STL specifications","created":"2024-03-23","cited_by_count":1}],"next_cursor":null}