def policy_fn(name, ob_space, ac_space):
# return mlp_policy.MlpPolicy(name=name, ob_space=ob_space, ac_space=ac_space,
# hid_size=args.policy_hidden_size, num_hid_layers=2, popart=args.popart, gaussian_fixed_var=args.fixed_var)
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
hid_size=[150, 50],
num_hid_layers=2,
popart=args.popart,
gaussian_fixed_var=args.fixed_var,
activation="relu")
def policy_fn(
name,
ob_space,
ac_space,
):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
hid_size=args.policy_hidden_size,
num_hid_layers=2,
popart=args.popart,
gaussian_fixed_var=args.fixed_var)