print("Using {} environments".format(n_envs))
# Create learning rate schedules for ppo2 and sac
if algo_ in ["ppo2", "sac", "td3"]:
for key in ['learning_rate', 'cliprange', 'cliprange_vf']:
if key not in hyperparams:
continue
if isinstance(hyperparams[key], str):
schedule, initial_value = hyperparams[key].split('_')
initial_value = float(initial_value)
hyperparams[key] = linear_schedule(initial_value)
elif isinstance(hyperparams[key], (float, int)):
# Negative value: ignore (ex: for clipping)
if hyperparams[key] < 0:
continue
hyperparams[key] = constfn(float(hyperparams[key]))
else:
raise ValueError('Invalid value for {}: {}'.format(
key, hyperparams[key]))
# Should we overwrite the number of timesteps?
if args.n_timesteps > 0:
if args.verbose:
print("Overwriting n_timesteps with n={}".format(
args.n_timesteps))
n_timesteps = args.n_timesteps
else:
n_timesteps = int(hyperparams['n_timesteps'])
normalize = False
normalize_kwargs = {}
log_path, "{}_{}".format(ENV_ID,
get_latest_run_id(log_path, ENV_ID) + 1))
params_path = os.path.join(save_path, ENV_ID)
os.makedirs(params_path, exist_ok=True)
# Create learning rate schedules for ppo2 and sac
if args.algo in ["ppo2", "sac"]:
for key in ['learning_rate', 'cliprange']:
if key not in hyperparams:
continue
if isinstance(hyperparams[key], str):
schedule, initial_value = hyperparams[key].split('_')
initial_value = float(initial_value)
hyperparams[key] = linear_schedule(initial_value)
elif isinstance(hyperparams[key], float):
hyperparams[key] = constfn(hyperparams[key])
else:
raise ValueError('Invalid valid for {}: {}'.format(
key, hyperparams[key]))
# Should we overwrite the number of timesteps?
if args.n_timesteps > 0:
n_timesteps = args.n_timesteps
else:
n_timesteps = int(hyperparams['n_timesteps'])
del hyperparams['n_timesteps']
normalize = False
normalize_kwargs = {}
if 'normalize' in hyperparams.keys():
normalize = hyperparams['normalize']
