Year: 2020
Type: preprint
Abstract: Most recently developed approaches to cooperative multi-agent reinforcement learning in the \emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function. In this paper, we demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches on popular multi-agent benchmark suite SMAC with little hyperparameter tuning. We also compare IPPO to several variants; the results suggest that IPPO's strong performance may be due to its robustness to some forms of environment non-stationarity.
Source: arXiv (Cornell University)
Institutions: University of Oxford, Nvidia (United States), Snap (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3099689767
