search

harman097 / RoboRugby

Training environment for ML agents in a competitive robot rugby game using OpenAI's gym standard.
MIT License
4 stars 0 forks source link

Proper gym setup #37

Closed harman097 closed 4 years ago

harman097 commented 4 years ago

https://github.com/openai/gym/blob/master/docs/creating-environments.md

There's some basic restructuring we need to do in order to properly load this as a gym which provides some wrapper functionality that's expected by TF models. (Ex. observation_spec(), action_spec(), etc.)

harman097 commented 4 years ago

Also a separate, tensorflow-specific guide here that's probly worth a read-through: https://www.tensorflow.org/agents/tutorials/2_environments_tutorial

harman097 commented 4 years ago

might need tweaked still to work with different models