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.
Source: DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement LearningPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Card Games | 1 | 25.00% |
Game of Poker | 1 | 25.00% |
Multi-agent Reinforcement Learning | 1 | 25.00% |
Reinforcement Learning (RL) | 1 | 25.00% |
Component | Type |
|
---|---|---|
DQN
|
Q-Learning Networks | |
Feedforward Network
|
Feedforward Networks | |
LSTM
|
Recurrent Neural Networks |