tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
Archived
1
Fork 0
Code Issues Releases Activity

fix(PPOTrainer.py): cleaned up + bug fixes regarding misuse of variable/wrong returns

Browse source
This commit is contained in:
Robin Meersman 2026-04-03 14:54:57 +02:00
parent 4396c9ac4b
commit a9302cfd4e
6 changed files with 133 additions and 88 deletions
Download patch file Download diff file Expand all files Collapse all files

3
experiments/train.py
View file

@ -1,5 +1,6 @@
import time
import torch
import tyro
from brittle_star_project.dataclasses import PPOArgs
@ -23,5 +24,7 @@ if __name__ == "__main__":
run_name = f"{args.exp_name}__seed_{args.seed}__{int(time.time())}"
env = make_env(args.config_path, args.num_envs)
torch.backends.cudnn.deterministic = args.torch_deterministic
ppo_trainer = PPOTrainer(args, env, run_name)
ppo_trainer.train()