Learning to Lead Themselves: Agentic AI in MAS using MARL

2025/09/24 by Ansh Kamthan, Kamthan, Ansh
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2510.00022

openalex publication_date 2025/09/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As autonomous systems move from prototypes to real deployments, the ability of multiple agents to make decentralized, cooperative decisions becomes a core requirement. This paper examines how agentic artificial intelligence, agents that act independently, adaptively and proactively can improve task allocation and coordination in multi-agent systems, with primary emphasis on drone delivery and secondary relevance to warehouse automation. We formulate the problem in a cooperative multi-agent reinforcement learning setting and implement a lightweight multi-agent Proximal Policy Optimization, called IPPO, approach in PyTorch under a centralized-training, decentralized-execution paradigm. Experiments are conducted in PettingZoo environment, where multiple homogeneous drones or agents must self-organize to cover distinct targets without explicit communication.

Citations

• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
• Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations
• MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• PettingZoo: Gym for Multi-Agent Reinforcement Learning
• Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
• Lifelong Multi-Agent Path Finding in Large-Scale Warehouses
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
• The StarCraft Multi-Agent Challenge
• Unity: A General Platform for Intelligent Agents
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
• Deep Reinforcement Learning that Matters
• Proximal Policy Optimization Algorithms
• Value-Decomposition Networks For Cooperative Multi-Agent Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Counterfactual Multi-Agent Policy Gradients
• Asynchronous Methods for Deep Reinforcement Learning
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Trust Region Policy Optimization
• Adam: A Method for Stochastic Optimization
• A Formal Analysis and Taxonomy of Task Allocation in Multi-Robot Systems
• Coverage Control for Mobile Sensing Networks
• Planning and acting in partially observable stochastic domains

Related

• Programming and Deployment of Autonomous Swarms using Multi-Agent Reinforcement Learning
• Strategic Coordination for Evolving Multi-agent Systems: A Hierarchical Reinforcement and Collective Learning Approach
• Deep Reinforcement Learning for Multi-Agent Interaction
• Cooperative Multi-Agent Systems from the Reinforcement Learning Perspective – Challenges, Algorithms, and an Application
• Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances