About this document
Ismcr 2020 CRP 3 by Istvan Harmati is a document available to read on EtoBox.
The paper presents a modified Advantage Actor-Critic (A2C) algorithm tailored for multi-agent environments, enhancing its applicability in cooperative-competitive scenarios. The authors test their algorithm in a pursuit-evasion testbed, demonstrating its effectiveness in multi-agent reinforcement learning. The research contributes to the ongoing development of reinforcement learning strategies by optimizing existing algorithms for better performance in complex environments.
- Author
- Istvan Harmati
- Language
- EN