Agents

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games

Single source1 source9 Oct 2026

arXiv:2610.11663v1 Announce Type: new Abstract: Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.11663

← Back to all developments · Signals are a development reported by more than one source. See the methodology.