Closed visuallization closed 1 year ago
Okay I got this working for:
python examples/stable_baselines3_example.py --env_path=./examples/JumperHard/bin/JumperHard.app --speedup=8
python examples/clean_rl_example.py --env_path=./examples/JumperHard/bin/JumperHard.app --speedup=8
It does not yet work properly for:
gdrl --trainer=rllib --env=gdrl --env_path=./examples/JumperHard/bin/JumperHard.app --num_workers=10 --experiment=JumperHard --viz --speedup=8 --batched_sampling=True
gdrl --trainer=sf --env=gdrl --env_path=./examples/JumperHard/bin/JumperHard.app --num_workers=10 --experiment=JumperHard --viz --speedup=8 --batched_sampling=True
as rllib and sf do not support apple m1 gpu acceleration yet. Also see:
However it is quite likely that this will already work on older intel macs, but I can't confirm because I only have a m1.
This is great! Thank you
Feel free to merge if you are happy with it
Hey @edbeeching
I added macos support for stable baseline 3 wrapper:
python examples/stable_baselines3_example.py --env_path=./examples/JumperHard/bin/JumperHard.app --speedup=8
I haven't had time yet to look into ray, sf and clean rl yet.