RETALIATE: Learning Winning Policies in First-Person Shooter Games
Abstract
In this paper we present RETALIATE, an online reinforcement learning algorithm for developing winning policies in team first-person shooter games. RETALIATE has three crucial characteristics: (1) individual BOT behavior is fixed although not known in advance, therefore individual BOTS work as “plug-ins”, (2) RETALIATE models the problem of learning team tactics through a simple state formulation, (3) discount rates commonly used in Q-learning are not used. As a result of these characteristics, the application of the Q-learning algorithm results in the rapid exploration towards a winning policy against an opponent team. In our empirical evaluation we demonstrate that RETALIATE adapts well when the environment changes.1
Cite
Text
Smith et al. "RETALIATE: Learning Winning Policies in First-Person Shooter Games." AAAI Conference on Artificial Intelligence, 2007.Markdown
[Smith et al. "RETALIATE: Learning Winning Policies in First-Person Shooter Games." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/smith2007aaai-retaliate/)BibTeX
@inproceedings{smith2007aaai-retaliate,
title = {{RETALIATE: Learning Winning Policies in First-Person Shooter Games}},
author = {Smith, Megan and Lee-Urban, Stephen and Muñoz-Avila, Hector},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2007},
pages = {1801-1806},
url = {https://mlanthology.org/aaai/2007/smith2007aaai-retaliate/}
}