Enhanced Rolling Horizon Evolution Algorithm with Opponent Model Learning: Results for the Fighting Game AI Competition
This work addresses the problem of real-time AI decision-making in complex video games for game developers and AI researchers, though it is incremental as it builds on existing RHEA methods.
The authors tackled the challenge of creating AI for 2-player fighting games by combining Rolling Horizon Evolution Algorithm with opponent model learning, resulting in a bot that significantly outperformed all competitors in the 2018 FTGAIC and placed second in the 2019 competition.
The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policy-gradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner.