[3R5-GS-2] Machine learning

[3R5-GS-2-01] AlphaZeRS that Efficiently Target-oriented Search

〇Ryoji Sakuraoka¹, Syuichi Arimura², Yu Kono¹, Tatsuji Takahasi¹ (1. Tokyo Denki University, 2. Gradueate school of Tokyo Denki University)

Keywords:Reinforcement Learning, Neural Network, Deep Reinforcement Learning

Tree search is still important in the field of AI for Player versus Player, and AlphaZero combines tree search with machine learning.
On the other hand, AI is not only pursues simple performance but
also adjusts the difficulty level according to the opponent, is also considered important in servces. What is the most important a fighting style always achieves a desired win rate against the opponent, so AI is needed to achieve a natural objective win rate level
Risk-sensitive Satisficing (RS) is algorithm for target-oriented exploration.
we proposed AlphaZeRS, which changes the evaluation function of AlphaZero from PUCT to RS. RS feature quick search and discovery to the objective level, which may reduce the number of nodes. In this paper, we tested AlphaZeRS in terms of achieving the target win probability level against opponents of different strengths and saving node deployment through simulations of two-player games.