No AI summary available for this article.
Why It Matters
Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating strategic command selection from learned unit control allows different strategies to be selected for different opponents while reusing the same execution policy. This requires an executor that can follow different commands and measurable criteria for assessing whether it does so. We introduce a constrained command-conditioned Proximal Policy Optimization (PPO) policy, the executor, for MicroRTS, a real-time strategy environ...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.11663v1 · Indexed about 1 hour ago