search

edbeeching / godot_rl_agents

An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents
MIT License
942 stars 69 forks source link

feat(sb3): also track reward in tensorboard #113

Closed visuallization closed 1 year ago

visuallization commented 1 year ago

Added VecMonitor to SB3 example to also track the reward in tensorboard.

Current problem: This only works for single instances and not for several multithreaded instances/envs. Check out this post how multithreading could look like: https://medium.com/analytics-vidhya/understanding-openai-baseline-source-code-and-making-it-do-self-play-part-3-23eeeb6ab817