xiaowei-hu / pysc2-agents

This is a simple implementation of DeepMind's PySC2 RL agents.

Home Page:https://zhuanlan.zhihu.com/p/29246185?group_id=890682069733232640

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

why text the the trained model ,the agent don't move all the time!

zhoudoudou opened this issue · comments

i test author's model and my model (trained),but the the agent don.t move and i can operate the game incredibly.

I also find agents almost don't move during the training besides testing process.