2026 · Conference paper
Multi-agent Reinforcement Learning for Autonomous Mobile Robot Coordination
Safet Imamović, Nermin Goran
Advanced Technologies, Systems, and Applications XI (IAT 2026), Vol. 2. Lecture Notes in Networks and Systems, vol. 2278, Ch. 15. Springer.
Cooperative cleaning robots in a shared grid world, compared across centralised and decentralised learners: centralised PPO and joint DQN (Stable-Baselines3) against custom PyTorch IDQN, MAPPO and QMIX. Measures room coverage, steps to completion and coordination behaviour across training checkpoints.