{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"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":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"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":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103},{"id":"1807.09356","title":"Iterative Amortized Inference","created":"2018-07-24","cited_by_count":94},{"id":"1901.09006","title":"On the Limitations of Representing Functions on Sets","created":"2019-01-25","cited_by_count":90},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69},{"id":"2007.12306","title":"Value-Decomposition Multi-Agent Actor-Critics","created":"2020-07-24","cited_by_count":48},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39},{"id":"2312.01058","title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment","created":"2023-12-02","cited_by_count":39},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27},{"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":"2012.01399","title":"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER","created":"2020-12-02","cited_by_count":19},{"id":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19},{"id":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17},{"id":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14},{"id":"2312.15600","title":"Context-aware Communication for Multi-agent Reinforcement Learning","created":"2023-12-25","cited_by_count":13},{"id":"2412.06861","title":"CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing","created":"2024-12-09","cited_by_count":11},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7},{"id":"2306.02422","title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","created":"2023-06-04","cited_by_count":5},{"id":"2506.01482","title":"Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?","created":"2025-06-02","cited_by_count":4},{"id":"2510.03257","title":"Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?","created":"2025-09-26","cited_by_count":4},{"id":"2310.11846","title":"MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning","created":"2023-10-18","cited_by_count":3},{"id":"2502.16496","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","created":"2025-02-23","cited_by_count":1},{"id":"2510.13343","title":"AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions","created":"2025-10-15","cited_by_count":1}],"next_cursor":null}