Open access
Aug 2026
Decentralized Model-Based ACKTR for Large-Scale Multi-Agent Path Planning Under Partial Observability
This work formulate large-scale MAPP as a partially observable networked Markov decision process as a decentralized model-based Actor-Critic using the Kronecker-factored trust region (DM-ACKTR) algorithm, which consistently obtains the highest TCR and lowest CR.
Ye-Min Liu, Jin-Hao Yang, Xiang-Yu Ma et al.
· Electronics · 0 citations