{"total":117,"rows":[{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104,"area":null},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"area":null},{"id":"2107.00200","title":"Social Coordination and Altruism in Autonomous Driving","created":"2021-07-01","cited_by_count":28,"area":"driving"},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2110.08229","title":"Influencing Towards Stable Multi-Agent Interactions","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2104.11861","title":"Class-Incremental Experience Replay for Continual Learning under Concept Drift","created":"2021-04-24","cited_by_count":17,"area":null},{"id":"2107.14316","title":"Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training","created":"2021-07-29","cited_by_count":16,"area":null},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2112.03547","title":"Self-Organized Polynomial-Time Coordination Graphs","created":"2021-12-07","cited_by_count":15,"area":null},{"id":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14,"area":null},{"id":"2102.00824","title":"HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging","created":"2021-01-18","cited_by_count":13,"area":null},{"id":"2302.02792","title":"Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2201.01247","title":"Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients","created":"2022-01-04","cited_by_count":12,"area":null},{"id":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2211.15612","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","created":"2022-11-28","cited_by_count":12,"area":"offlinerl"},{"id":"2103.12710","title":"Spatial Intention Maps for Multi-Agent Mobile Manipulation","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2304.14656","title":"From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2104.06655","title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2111.00278","title":"A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles","created":"2021-10-30","cited_by_count":9,"area":null},{"id":"2204.12181","title":"Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach","created":"2022-04-26","cited_by_count":9,"area":null},{"id":"2206.13441","title":"EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2110.00121","title":"Emergence of Theory of Mind Collaboration in Multiagent Systems","created":"2021-09-30","cited_by_count":8,"area":null},{"id":"2310.03195","title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","created":"2023-10-04","cited_by_count":8,"area":null},{"id":"1909.11468","title":"Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems","created":"2019-09-25","cited_by_count":7,"area":"offlinerl"},{"id":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2403.15341","title":"Collaborative AI Teaming in Unknown Environments via Active Goal Deduction","created":"2024-03-22","cited_by_count":6,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2106.00543","title":"MARL with General Utilities via Decentralized Shadow Reward Actor-Critic","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2110.13621","title":"Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-level","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2201.10774","title":"Competition over data: how does data purchase affect users?","created":"2022-01-26","cited_by_count":5,"area":null},{"id":"2305.18875","title":"Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2401.04934","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2207.05886","title":"Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior","created":"2022-07-12","cited_by_count":4,"area":null},{"id":"2303.17655","title":"Q-Learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2311.11280","title":"Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part II: Control-Aware Radio Resource Allocation","created":"2023-11-19","cited_by_count":4,"area":null},{"id":"2505.17734","title":"URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles","created":"2025-05-23","cited_by_count":4,"area":"driving"},{"id":"2509.16606","title":"Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2103.12070","title":"Learning to Robustly Negotiate Bi-Directional Lane Usage in High-Conflict Driving Scenarios","created":"2021-03-22","cited_by_count":3,"area":"driving"},{"id":"2103.15941","title":"Shaping Advice in Deep Multi-Agent Reinforcement Learning","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2112.01765","title":"Learning Emergent Random Access Protocol for LEO Satellite Networks","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2203.08454","title":"Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents","created":"2022-03-16","cited_by_count":3,"area":null},{"id":"2408.07098","title":"QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2506.04251","title":"Language-Driven Coordination and Learning in Multi-Agent Simulation Environments","created":"2025-06-01","cited_by_count":3,"area":"agents"},{"id":"2101.02308","title":"Coding for Distributed Multi-Agent Reinforcement Learning","created":"2021-01-07","cited_by_count":2,"area":null},{"id":"2102.12957","title":"Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2109.14188","title":"Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2111.11229","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2212.07967","title":"Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet","created":"2022-12-15","cited_by_count":2,"area":null},{"id":"2308.14308","title":"Policy Diversity for Cooperative Agents","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2311.03756","title":"Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2407.04259","title":"Q-Learning under Finite Model Uncertainty","created":"2024-07-05","cited_by_count":2,"area":"deeprl"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2102.09139","title":"Algorithmic pricing with independent learners and relative experience replay","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2104.13446","title":"Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2110.05125","title":"Non-Parametric Neuro-Adaptive Coordination of Multi-Agent Systems","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2110.12929","title":"Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2111.15087","title":"MAMRL: Exploiting Multi-agent Meta Reinforcement Learning in WAN Traffic Engineering","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2202.05135","title":"Group-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2208.02424","title":"Transferable Multi-Agent Reinforcement Learning with Dynamic Participating Agents","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2303.07393","title":"Many learning agents interacting with an agent-based market model","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2304.09547","title":"Graph Exploration for Effective Multi-agent Q-Learning","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2308.09219","title":"Learning in Cooperative Multiagent Systems Using Cognitive and Machine Models","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2502.13188","title":"Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing","created":"2025-02-18","cited_by_count":1,"area":"driving"},{"id":"2508.10423","title":"MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2603.06813","title":"Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.09028","title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","created":"2026-04-10","cited_by_count":1,"area":"moe"},{"id":"2605.15207","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","created":"2026-05-01","cited_by_count":1,"area":"agents"},{"id":"2102.00847","title":"CoordiQ : Coordinated Q-learning for Electric Vehicle Charging Recommendation","created":"2021-01-28","cited_by_count":0,"area":null},{"id":"2109.05429","title":"EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles","created":"2021-09-12","cited_by_count":0,"area":null},{"id":"2112.12458","title":"Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning","created":"2021-12-23","cited_by_count":0,"area":null},{"id":"2202.07275","title":"HiMA: A Fast and Scalable History-based Memory Access Engine for Differentiable Neural Computer","created":"2022-02-15","cited_by_count":0,"area":null},{"id":"2202.09489","title":"Shaping Advice in Deep Reinforcement Learning","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2203.02896","title":"Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation","created":"2022-03-06","cited_by_count":0,"area":null},{"id":"2211.01266","title":"Knowing the Past to Predict the Future: Reinforcement Virtual Learning","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2212.07942","title":"Multi-Agent Dynamic Pricing in a Blockchain Protocol Using Gaussian Bandits","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2212.13379","title":"Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization","created":"2022-12-27","cited_by_count":0,"area":null},{"id":"2302.12403","title":"Plume: A Framework for High Performance Deep RL Network Controllers via Prioritized Trace Sampling","created":"2023-02-24","cited_by_count":0,"area":null},{"id":"2303.01070","title":"GHQ: Grouped Hybrid Q Learning for Heterogeneous Cooperative Multi-agent Reinforcement Learning","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2303.09058","title":"SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.05573","title":"An Algorithm For Adversary Aware Decentralized Networked MARL","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2305.17372","title":"Reinforcement Learning With Reward Machines in Stochastic Games","created":"2023-05-27","cited_by_count":0,"area":null},{"id":"2402.06117","title":"Spatially-Attentive Patch-Hierarchical Network with Adaptive Sampling for Motion Deblurring","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2406.07848","title":"Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2410.15876","title":"FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2411.07413","title":"ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting","created":"2024-11-11","cited_by_count":0,"area":null}],"next_cursor":"100"}