search

PWhiddy / PokemonRedExperiments

Playing Pokemon Red with Reinforcement Learning
MIT License
7k stars 645 forks source link

About Visualization #183

Open onekid opened 3 months ago

onekid commented 3 months ago

This project is amazing！I already experienced the pre-trained model. But I don't know how to visualize this training process. where should i put these config? ↓

env = StreamWrapper( env, stream_metadata = { # All of this is part is optional "user": "pw", # choose your own username "env_id": id, # environment identifier "color": "#0033ff", # choose your color :) "extra": "", # any extra text you put here will be displayed } )

If I could train the model while visually observing the model，That would be really nice!

PWhiddy commented 3 months ago

Hi! You put it after where you've initialized your environment. So if you're using run_baseline_parallel_fast, right after here: https://github.com/PWhiddy/PokemonRedExperiments/blob/ecea155c265e7cad0d500b3f65b7b872918f752b/baselines/run_baseline_parallel_fast.py#L21