DouZero

2000년 도입 · 논문 4편에서 사용

DouZero is an AI system for the card game DouDizhu that enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. The Q-network of DouZero consists of an LSTM to encode historical actions and six layers of MLP with hidden dimension of 512. The network predicts a value for a given state-action pair based on the concatenated representation of action and state.

출처: DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

소개 논문: DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning