ABL Wargus

wargus1_0.png

Team

Ben Weber, Josh McCoy

Advisor

Michael Mateas

Research Lab

Expressive Intelligence Studio

Overview

The goal of ABL Wargus is to develop an adaptive artificial intelligence (AI) for real-time strategy (RTS) games using a reactive planner. Based on an analysis of how skilled human players conceptualize RTS gameplay, we partition the problem space into domains of competence seen in expert human play. The agent consists of the following components:

  • Strategy Manager: Makes high-level strategy decisions
  • Production Manager: Determines which units and buildings to produce
  • Tactics Manager: Manages small-scale combat
  • Income Manager: Controls worker units to harvest resources
  • Scouting Manager: Handles reconnaissance

It has also been extended with case-based reasoning to learn build orders from replays, reducing the amount of knowledge that needs to be hardcoded. The agent architecture is shown below:

Images

Click images to enlarge.
Syndicate content Syndicate content Syndicate content

Publications

Weber, B. G., and M. Mateas, "Conceptual Neighborhoods for Retrieval in Case-Based Reasoning", ICCBR ’09: Proceedings of the 8th International Conference on Case-Based Reasoning, Berlin, Heidelberg, Springer-Verlag, pp. 343–357, 2009.  Download: iccbr_2009.pdf (159.38 KB)
Weber, B. G., and M. Mateas, "Case-Based Reasoning for Build Order in Real-Time Strategy Games", Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2009), 10/2009.  Download: bweber_aiide_09.pdf (80.96 KB)
McCoy, J., and M. Mateas, "An integrated agent for playing real-time strategy games", AAAI’08: Proceedings of the 23rd national conference on Artificial intelligence: AAAI Press, pp. 1313–1318, 2008.  Download: AAAI08Mccoy.pdf (199.38 KB)