Weirui Ye

Results 17 comments of Weirui Ye

Question about whether need to train multiple agents for different games

Each game needs to train an agent separately. The dynamics function takes in the actions, and the policy function outputs the actions. Since different environments have different actions and the...

Question about getting zero test score when I try to run EfficientZero on BabyAI grid environment

Hi, I noticed that you have changed "(image_channel,96,96) to (image_channel,7,7)". Is the observation shape of your environment 7x7? Noticed that there exists a downsampling network in model.py, which tries to...

Code for continuous action space

Yes, it is coming soon. Thank you for your attention.

Question about the index of pad_child_visits_lst in selfplay_worker.py

Thank you for your correction. I think it should be a bug. Except for the observation history, all the other statistics (eg, visits, values, rewards) should be indexed from 0...

Question about the transform between true reward and value prefix

Thank you for your correction! You are right. It is a bug that results in wrong min/max values on the tree side. Really thank you for your detailed reading. And...

EfficientZero V2

Yes, it is coming soon. Thank you for your attention.

Question about the effect of state encoding indentity connection in dynamics network

Thank you for your comments. The identity connection here follows the same architecture of resnets. The residual part provides richer and better gradients when the network is deep. Considering the...