Multi-Agent Reinforcement Learning
Also known as MARL
Overview
Multi-agent reinforcement learning studies how multiple decision-makers learn when each agent’s actions affect both the environment and other agents, across cooperative, competitive, and mixed-motive settings. Common approaches include centralized training with decentralized execution, independent or shared actor-critic policies, value factorization such as QMIX, self-play and game-solving methods, and graph-based communication or hierarchical policies. Researchers test these methods in benchmarks such as SMAC, MPE, Overcooked, and multi-agent MuJoCo, and apply them to robotics, traffic, wireless networks, energy systems, and language-agent workflows. A central challenge is scaling coordination and credit assignment while keeping learning stable under non-stationarity and policies robust, safe, and fair with unfamiliar partners and conditions.
Latest papers
402 papers37 papers in the last four weeks, down 27% on the four weeks before. 0.3% of all new papers.
Robust and Efficient Communication for Multi-Agent Learning
DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat
leader'' and supporter''). Conditioned on these roles and encoded graph-relational features, a low-level policy executes discrete maneuver actions, facilitating the joint optimization of tactical strategy and collaborative execution. Furthermore, a target-priority auxiliary task is designed to foster the emergence of behaviors such as focus-fire. Experimental results demonstrate that DRG-MAPPO achieves a state-of-the-art win rate of 87%, suggesting that our framework effectively balances relational modeling, interpretability, and optimization stability for cooperative air combat.Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response
SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems
Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding
An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback
From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
Low-Altitude Fluid Antenna Network with Multi-Agent Reinforcement Learning
LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games
SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
Simulating Cognitive Smart Freight Corridors with Agent-Based Models and Reinforcement Learning
Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning
Multi-Agent Off-Policy Deep Reinforcement Learning for Smart Campus Coverage
RoboStriker: Latent-Space Strategic Games for Autonomous Humanoid Boxing
AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning
OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways
Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry
mQ-learning and mQ-learning-intervals, achieving regret, where is the horizon, the state count, the total steps, and the joint action space across players. For Problem C we give mEXC and mEXC-Bellman, two-phase explore-then-commit algorithms with regret . Against the centralized joint-action benchmark, decentralized learning under information asymmetry matches the single-agent Q-learning rate of \cite{jin2018q} up to logarithmic factors. Because grows exponentially in , the bounds are most meaningful for small or small per-player action sets.