Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

18 Nov 2020 • Christian Schroeder de Witt • Tarun Gupta • Denys Makoviichuk • Viktor Makoviychuk • Philip H. S. Torr • Mingfei Sun • Shimon Whiteson

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... (read more)

PDF Abstract

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Entropy Regularization	Regularization
PPO	Policy Gradient Methods

METHOD

TYPE

Entropy Regularization

Regularization

PPO

Policy Gradient Methods

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods used in the Paper

Add Remove

Edit Social Preview

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? Edit social preview

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods used in the Paper Edit Add Remove

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods used in the Paper

Add Remove