Chris Pollett > Students >
Luo

    ( Print View)

    [Bio]

    [Blog]

    [CS 297 Proposal]

    [Deliverable 1]

    [Deliverable 2]

    [Deliverable 3]

    [Deliverable 4]

    [AI Methods for Dou Di Zhu-PDF]

    [Q-learning-PDF]

    [CS297 Report-PDF]

    [CS 298 Proposal]

    [CS298_Report-PDF]

    [Defense Slides-PDF]

Dou Di Zhu with Rule-Based

I use the python3 to re-implement an exist Rule-Based method for Dou Di Zhu

In this part, I prepare three AI agents to follow the same Rule-Based's knowledge base to play the game.

As, Based-rule method doesn't need to training part, so I test it for 1000 times.

1000 training times, 200 testing time result:
  • Player0 peasant winning rate: 56.14%
  • Player0 landlord winning rate: 41.87%
  • Player0 winning rate: 51.4%
  • Player1 peasant winning rate: 57.98%
  • Player1 landlord winning rate: 45.54%
  • Player1 winning rate: 53.8%
  • Player2 peasant winning rate: 56.29%
  • Player2 landlord winning rate: 42.17%
  • Player2 winning rate: 51.6%

I test many times, and the results are very stable.

It's based on Python 3. Just run the 'RuleBased.py' to run this project.

Deliverable 4.zip (You need to install the random library in your Python 3)