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, PPOArgs.py): added hyperparam config path to cli args, fixed missing arguments error in _step call

Browse source
This commit is contained in:
Robin Meersman 2026-04-06 14:07:46 +02:00
parent ab7fa1584f
commit 8a2f8b14bc
3 changed files with 16 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
experiments/PPOTrainer.py
View file

@ -500,12 +500,14 @@ class PPOTrainer:
iter_bar = tqdm.tqdm( iter_bar = tqdm.tqdm(
range(1, self.args.num_iterations + 1), range(1, self.args.num_iterations + 1),
disable=not sys.stdout.isatty(), disable=not is_tty,
) )
for iteration in iter_bar: for iteration in iter_bar:
iteration_time_start = time.time() iteration_time_start = time.time()
env_state, next_obs, next_done, loss_info = self._step(env_state, next_obs, next_done) env_state, next_obs, next_done, loss_info = self._step(
env_state, next_obs, next_done, is_tty=is_tty, iteration=iteration
)
if not is_tty and iteration == 1: if not is_tty and iteration == 1:
print(f">>> [HPC] First rollout completed: {time.ctime()}", flush=True) print(f">>> [HPC] First rollout completed: {time.ctime()}", flush=True)

12
experiments/train.py
View file

@ -17,11 +17,14 @@ def make_env(config_path: str | None, num_envs: int) -> BrittleStarJaxEnvWrapper
return BrittleStarJaxEnvWrapper.from_config(config_path, num_envs=num_envs) return BrittleStarJaxEnvWrapper.from_config(config_path, num_envs=num_envs)
def parse_args() -> PPOArgs: def parse_args(log: bool = True) -> PPOArgs:
temp_args = tyro.cli(PPOArgs) temp_args = tyro.cli(PPOArgs)
if temp_args.env_config_path is not None: if temp_args.hyperparameter_config_path is not None:
with open(temp_args.env_config_path, "r") as f: if log:
print(f"Loading hyperparameter config from {temp_args.hyperparameter_config_path}")
with open(temp_args.hyperparameter_config_path, "r") as f:
config = yaml.safe_load(f) config = yaml.safe_load(f)
if config: if config:
# parse PPOArgs with defaults from yaml. # parse PPOArgs with defaults from yaml.
@ -32,6 +35,9 @@ def parse_args() -> PPOArgs:
# Reparse CLI to ensure they OVERRIDE the yaml # Reparse CLI to ensure they OVERRIDE the yaml
args = tyro.cli(PPOArgs, default=temp_args) args = tyro.cli(PPOArgs, default=temp_args)
else: else:
if log:
print("No hyperparameter config provided, using default config")
args = temp_args args = temp_args
return args return args

3
src/brittle_star_project/dataclasses/PPOArgs.py
View file

@ -13,6 +13,9 @@ class PPOArgs:
# path to environment config file, if None, use default config # path to environment config file, if None, use default config
env_config_path: str | None = None env_config_path: str | None = None
# path to hyperparameter config file (yaml), if None, use default config
hyperparameter_config_path: str | None = None
# the name of this experiment # the name of this experiment
exp_name: str = "brittle_star_ppo" exp_name: str = "brittle_star_ppo"