def policy_fn(name, ob_space, ac_space, reuse=False):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
reuse=reuse,
hid_size=args.policy_hidden_size,
num_hid_layers=2)
def policy_fn(name, ob_space, ac_space, reuse=False):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
reuse=reuse,
hid_size=args.policy_hidden_size,
num_hid_layers=2,
gaussian_fixed_var=args.gaussian_fixed_var,
obs_normalize=args.obs_normalize)
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)
def policy_fn(name,
ob_space,
ac_space,
reuse=False,
placeholders=None,
sess=None):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
reuse=reuse,
sess=sess,
hid_size=args.policy_hidden_size,
num_hid_layers=2,
placeholders=placeholders)
def policy_fn(name, ob_space, ac_space, reuse=False):
return mlp_policy.MlpPolicy(name=name, reuse=reuse,
ob_space=ob_space, ac_space=ac_space,
**policy_kwargs)
def _policy_fn(name, ob_space, ac_space, reuse=False, sess=None):
return mlp_policy.MlpPolicy(name=name, ob_space=ob_space, ac_space=ac_space, sess=sess,
reuse=reuse, hid_size=policy_hidden_size, num_hid_layers=2)
