def test_vec_env(tmpdir):
"""Test VecNormalize Object"""
clip_obs = 0.5
clip_reward = 5.0
orig_venv = DummyVecEnv([make_env])
norm_venv = VecNormalize(orig_venv,
norm_obs=True,
norm_reward=True,
clip_obs=clip_obs,
clip_reward=clip_reward)
_, done = norm_venv.reset(), [False]
while not done[0]:
actions = [norm_venv.action_space.sample()]
obs, rew, done, _ = norm_venv.step(actions)
assert np.max(np.abs(obs)) <= clip_obs
assert np.max(np.abs(rew)) <= clip_reward
path = str(tmpdir.join("vec_normalize"))
norm_venv.save(path)
deserialized = VecNormalize.load(path, venv=orig_venv)
check_vec_norm_equal(norm_venv, deserialized)
def single_wrappers(
single_venv,
scheduler,
our_idx,
normalize,
normalize_observations,
rew_shape,
rew_shape_params,
embed_index,
embed_paths,
embed_types,
debug,
env_name,
load_policy,
lookback_params,
transparent_params,
log_callbacks,
save_callbacks,
):
if rew_shape:
rew_shape_venv = apply_reward_wrapper(
single_env=single_venv,
scheduler=scheduler,
shaping_params=rew_shape_params,
agent_idx=our_idx,
)
log_callbacks.append(LoggerOnlyLogCallback(rew_shape_venv))
single_venv = rew_shape_venv
for anneal_type in ["noise", "rew_shape"]:
if scheduler.is_conditional(anneal_type):
scheduler.set_annealer_get_logs(anneal_type,
rew_shape_venv.get_logs)
if lookback_params["lb_num"] > 0:
if len(embed_types) > 1:
raise ValueError(
"Lookback is not supported with multiple embedded agents")
embed_path = embed_paths[0]
embed_type = embed_types[0]
lookback_venv = LookbackRewardVecWrapper(
single_venv,
env_name,
debug,
embed_index,
embed_path,
embed_type,
transparent_params,
**lookback_params,
)
single_venv = lookback_venv
if normalize:
if normalize_observations:
if load_policy["path"] is not None:
if load_policy["type"] == "zoo":
raise ValueError(
"Trying to normalize twice. Bansal et al's Zoo agents normalize "
"implicitly. Please set normalize=False to disable VecNormalize."
)
normalized_venv = VecNormalize(single_venv)
else:
normalized_venv = VecNormalize(single_venv, norm_obs=False)
if load_policy["path"] is not None and load_policy["type"] != "zoo":
normalized_venv.load_running_average(load_policy["path"])
save_callbacks.append(lambda root_dir: normalized_venv.save(
os.path.join(root_dir, "vec_normalize.pkl")))
single_venv = normalized_venv
return single_venv