Our project aims to train an AI agent to play Hanabi and achieve high scores using reinforcement learning. We will use PPO and A2C to optimize decision-making in a cooperative, partially observable environment.

Github: Source code

Pages:

• Proposal
• Status
• Final
• Team Details
  
  

Resources links:

1. Hanabi Learning Environment
2. Stable baselines3
3. Hanabi rule
4. Learning and Reproduction