Closed zenoengine closed 2 years ago
Hello! Thanks for solving our problem. Thanks to your contribution, I checked that mlagents run without error in Windows. However, I got this error when I ran Atari env. Can you check about this error when running with Atari?
@leonard-q Hello, Thank you for reviewing! I added the missing code.
@zenoengine Thank you! I tested it with [single_train.py, sync_distributed_train] [DQN, PPO] [atari, hopper_mlagent, pong_mlagent] It worked without error in above algorithms and envs. It solves one of our big problem! Thanks for your contribution! :)
:star2: Hello! Thanks for contributing JORLDY!
Checklist
Please check if you consider the following items.
Types of changes
Bugfix
Test Configuration
Description
The basic idea is that eval_manager in the child process should create its env. For now, distributed_train.py process doesn’t use env after creating agent config.