Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Gym-$\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
arXiv (Cornell University)
21 May 2021
Abstract
In recent years, researchers have achieved great success in applying Deep
Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games,
creating strong autonomous agents that could defeat professional players in
StarCraft~II. However, existing approaches to tackle full games have high
computational costs, usually requiring the use of thousands of GPUs and CPUs
for weeks. This paper has two main contributions to address this issue: 1) We
introduce Gym-$\mu$RTS (pronounced "gym-micro-RTS") as a fast-to-run RL
environment for full-game RTS research and 2) we present a collection of
techniques to scale DRL to play full-game $\mu$RTS as well as ablation studies
to demonstrate their empirical importance. Our best-trained bot can defeat
every $\mu$RTS bot we tested from the past $\mu$RTS competitions when working
in a single-map setting, resulting in a state-of-the-art DRL agent while only
taking about 60 hours of training using a single machine (one GPU, three vCPU,
16GB RAM). See the blog post at
https://wandb.ai/vwxyzjn/gym-microrts-paper/reports/Gym-RTS-Toward-Affordable-Deep-Reinforcement-Learning-Research-in-Real-Time-Strategy-Games--Vmlldzo2MDIzMTg
and the source code at https://github.com/vwxyzjn/gym-microrts-paper
Metrics
17 Record Views
Details
- Title
- Gym-$\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
- Creators
- Shengyi HuangSantiago OntañónChris BamfordLukasz Grela
- Publication Details
- arXiv (Cornell University)
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Other Identifier
- 991021869012704721