Daochen Zha
Daochen Zha
@systats Thanks for the information. The platform looks really cool.
@systats I very much like to promote the platform since it really looks cool to me. I feel like RLCard can be an offline testing environment to help people create...
@systats I have glanced at the interfaces of pokerwars. I feel like some efforts would be needed in state representation if we want to wrap RLCard using the bot keleton....
@zedwei Thanks a lot! it is a very good point that we didn't notice before. I agree with you that it will be better to remove illegal actions before the...
@zedwei Tractor should be very similar to DouDizhu (large action space, but only small parts it is legal). I think there is no one working on the tractor. Contributions are...
I think so. GIven enough training, the agent should gradually learn these skills.
@zedwei Thanks for the feedback! Yes, I agree with you. But I am hesitating what is the most efficient way to implement this. I expect we need to save the...
@zedwei I have implemented this. See https://github.com/datamllab/rlcard/blob/dmc/rlcard/agents/dqn_agent.py#L195-L200 Interestingly, when I run on Dou Dizhu, I didn't observe a clear difference.
@DonaldTsang Hi, thank you for providing all those useful resources. We will carefully check them out.
@WhymustIhaveaname Thanks for the information. Yes, we are very happy to include Gongzhu. Gongzhu has a similar GUI as DouDizhu. It should not be hard to adapt the GUI in...