Year: 2025
Type: preprint
Abstract: We present an adapter-based approach for tactical conditioning of StarCraft II AI agents. Current agents, while powerful, lack the ability to adapt their strategies based on high-level tactical directives. Our method freezes a pre-trained policy network (DI-Star) and attaches lightweight adapter modules to each action head, conditioned on a tactical tensor that encodes strategic preferences. By training these adapters with KL divergence constraints, we ensure the policy maintains core competencies while exhibiting tactical variations. Experimental results show our approach successfully modulates agent behavior across tactical dimensions including aggression, expansion patterns, and technology preferences, while maintaining competitive performance. Our method enables flexible tactical control with minimal computational overhead, offering practical strategy customization for complex real-time strategy games.
Source: arXiv (Cornell University)
Authors: Ma, Weiyu, Jiang, Jiwen, Fu, Haobo, Zhang, Haifeng
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417493408