Modify train files, eval_manager

zenoengine commented 2 years ago

:star2: Hello! Thanks for contributing JORLDY!

Checklist

Please check if you consider the following items.

[v] My code follows the style guidelines of this project
[v] My code follows the naming convention of documentation
[v] I have commented my code, particularly in hard-to-understand areas
[v] My changes generate no new warnings or errors

Types of changes

Bugfix

Test Configuration

OS: Windows 10
Python version: 3.8
Additional libraries: None

Description

Fixed #44

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.

leonard-q commented 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?

zenoengine commented 2 years ago

@leonard-q Hello, Thank you for reviewing! I added the missing code.

leonard-q commented 2 years ago

@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! :)

kakaoenterprise / JORLDY