mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-17 08:56:08 +00:00
Add test for predict method
This commit is contained in:
parent
8b559d71ab
commit
e31b139c47
4 changed files with 75 additions and 30 deletions
55
tests/test_predict.py
Normal file
55
tests/test_predict.py
Normal file
|
|
@ -0,0 +1,55 @@
|
||||||
|
import gym
|
||||||
|
import pytest
|
||||||
|
|
||||||
|
from torchy_baselines import A2C, CEMRL, PPO, SAC, TD3
|
||||||
|
from torchy_baselines.common.vec_env import DummyVecEnv
|
||||||
|
|
||||||
|
MODEL_LIST = [
|
||||||
|
CEMRL,
|
||||||
|
PPO,
|
||||||
|
A2C,
|
||||||
|
TD3,
|
||||||
|
SAC,
|
||||||
|
]
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("model_class", MODEL_LIST)
|
||||||
|
def test_auto_wrap(model_class):
|
||||||
|
# test auto wrapping of env into a VecEnv
|
||||||
|
env = gym.make('Pendulum-v0')
|
||||||
|
eval_env = gym.make('Pendulum-v0')
|
||||||
|
model = model_class('MlpPolicy', env)
|
||||||
|
model.learn(100, eval_env=eval_env)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("model_class", MODEL_LIST)
|
||||||
|
def test_predict(model_class):
|
||||||
|
# test detection of different shapes by the predict method
|
||||||
|
model = model_class('MlpPolicy', 'Pendulum-v0')
|
||||||
|
env = gym.make('Pendulum-v0')
|
||||||
|
vec_env = DummyVecEnv([lambda: gym.make('Pendulum-v0'), lambda: gym.make('Pendulum-v0')])
|
||||||
|
|
||||||
|
obs = env.reset()
|
||||||
|
action = model.predict(obs)
|
||||||
|
assert action.shape == env.action_space.shape
|
||||||
|
assert env.action_space.contains(action)
|
||||||
|
|
||||||
|
vec_env_obs = vec_env.reset()
|
||||||
|
action = model.predict(vec_env_obs)
|
||||||
|
assert action.shape[0] == vec_env_obs.shape[0]
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("model_class", [A2C, PPO])
|
||||||
|
def test_predict_discrete(model_class):
|
||||||
|
# test detection of different shapes by the predict method
|
||||||
|
model = model_class('MlpPolicy', 'CartPole-v1')
|
||||||
|
env = gym.make('CartPole-v1')
|
||||||
|
vec_env = DummyVecEnv([lambda: gym.make('CartPole-v1'), lambda: gym.make('CartPole-v1')])
|
||||||
|
|
||||||
|
obs = env.reset()
|
||||||
|
action = model.predict(obs)
|
||||||
|
assert action.shape == ()
|
||||||
|
assert env.action_space.contains(action)
|
||||||
|
|
||||||
|
vec_env_obs = vec_env.reset()
|
||||||
|
action = model.predict(vec_env_obs)
|
||||||
|
assert action.shape[0] == vec_env_obs.shape[0]
|
||||||
|
|
@ -14,18 +14,12 @@ def test_td3(action_noise):
|
||||||
model = TD3('MlpPolicy', 'Pendulum-v0', policy_kwargs=dict(net_arch=[64, 64]),
|
model = TD3('MlpPolicy', 'Pendulum-v0', policy_kwargs=dict(net_arch=[64, 64]),
|
||||||
learning_starts=100, verbose=1, create_eval_env=True, action_noise=action_noise)
|
learning_starts=100, verbose=1, create_eval_env=True, action_noise=action_noise)
|
||||||
model.learn(total_timesteps=1000, eval_freq=500)
|
model.learn(total_timesteps=1000, eval_freq=500)
|
||||||
model.save("test_save")
|
|
||||||
model.load("test_save")
|
|
||||||
os.remove("test_save.zip")
|
|
||||||
|
|
||||||
|
|
||||||
def test_cemrl():
|
def test_cemrl():
|
||||||
model = CEMRL('MlpPolicy', 'Pendulum-v0', policy_kwargs=dict(net_arch=[16]), pop_size=2, n_grad=1,
|
model = CEMRL('MlpPolicy', 'Pendulum-v0', policy_kwargs=dict(net_arch=[16]), pop_size=2, n_grad=1,
|
||||||
learning_starts=100, verbose=1, create_eval_env=True, action_noise=action_noise)
|
learning_starts=100, verbose=1, create_eval_env=True, action_noise=action_noise)
|
||||||
model.learn(total_timesteps=1000, eval_freq=500)
|
model.learn(total_timesteps=1000, eval_freq=500)
|
||||||
model.save("test_save")
|
|
||||||
model.load("test_save")
|
|
||||||
os.remove("test_save.zip")
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize("model_class", [A2C, PPO])
|
@pytest.mark.parametrize("model_class", [A2C, PPO])
|
||||||
|
|
@ -33,9 +27,6 @@ def test_cemrl():
|
||||||
def test_onpolicy(model_class, env_id):
|
def test_onpolicy(model_class, env_id):
|
||||||
model = model_class('MlpPolicy', env_id, policy_kwargs=dict(net_arch=[16]), verbose=1, create_eval_env=True)
|
model = model_class('MlpPolicy', env_id, policy_kwargs=dict(net_arch=[16]), verbose=1, create_eval_env=True)
|
||||||
model.learn(total_timesteps=1000, eval_freq=500)
|
model.learn(total_timesteps=1000, eval_freq=500)
|
||||||
model.save("test_save")
|
|
||||||
model.load("test_save")
|
|
||||||
os.remove("test_save.zip")
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize("ent_coef", ['auto', 0.01])
|
@pytest.mark.parametrize("ent_coef", ['auto', 0.01])
|
||||||
|
|
@ -44,6 +35,3 @@ def test_sac(ent_coef):
|
||||||
learning_starts=100, verbose=1, create_eval_env=True, ent_coef=ent_coef,
|
learning_starts=100, verbose=1, create_eval_env=True, ent_coef=ent_coef,
|
||||||
action_noise=NormalActionNoise(np.zeros(1), np.zeros(1)))
|
action_noise=NormalActionNoise(np.zeros(1), np.zeros(1)))
|
||||||
model.learn(total_timesteps=1000, eval_freq=500)
|
model.learn(total_timesteps=1000, eval_freq=500)
|
||||||
model.save("test_save")
|
|
||||||
model.load("test_save")
|
|
||||||
os.remove("test_save.zip")
|
|
||||||
|
|
|
||||||
|
|
@ -134,6 +134,7 @@ def test_exclude_include_saved_params(model_class):
|
||||||
# clear file from os
|
# clear file from os
|
||||||
os.remove("test_save.zip")
|
os.remove("test_save.zip")
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize("model_class", [SAC, TD3])
|
@pytest.mark.parametrize("model_class", [SAC, TD3])
|
||||||
def test_save_load_replay_buffer(model_class):
|
def test_save_load_replay_buffer(model_class):
|
||||||
log_folder = 'logs'
|
log_folder = 'logs'
|
||||||
|
|
|
||||||
|
|
@ -335,24 +335,25 @@ class BaseRLModel(ABC):
|
||||||
else:
|
else:
|
||||||
raise ValueError("Error: Unexpected observation shape {} for ".format(observation.shape) +
|
raise ValueError("Error: Unexpected observation shape {} for ".format(observation.shape) +
|
||||||
"Discrete environment, please use (1,) or (n_env, 1) for the observation shape.")
|
"Discrete environment, please use (1,) or (n_env, 1) for the observation shape.")
|
||||||
elif isinstance(observation_space, gym.spaces.MultiDiscrete):
|
# TODO: add support for MultiDiscrete and MultiBinary action spaces
|
||||||
if observation.shape == (len(observation_space.nvec),):
|
# elif isinstance(observation_space, gym.spaces.MultiDiscrete):
|
||||||
return False
|
# if observation.shape == (len(observation_space.nvec),):
|
||||||
elif len(observation.shape) == 2 and observation.shape[1] == len(observation_space.nvec):
|
# return False
|
||||||
return True
|
# elif len(observation.shape) == 2 and observation.shape[1] == len(observation_space.nvec):
|
||||||
else:
|
# return True
|
||||||
raise ValueError("Error: Unexpected observation shape {} for MultiDiscrete ".format(observation.shape) +
|
# else:
|
||||||
"environment, please use ({},) or ".format(len(observation_space.nvec)) +
|
# raise ValueError("Error: Unexpected observation shape {} for MultiDiscrete ".format(observation.shape) +
|
||||||
"(n_env, {}) for the observation shape.".format(len(observation_space.nvec)))
|
# "environment, please use ({},) or ".format(len(observation_space.nvec)) +
|
||||||
elif isinstance(observation_space, gym.spaces.MultiBinary):
|
# "(n_env, {}) for the observation shape.".format(len(observation_space.nvec)))
|
||||||
if observation.shape == (observation_space.n,):
|
# elif isinstance(observation_space, gym.spaces.MultiBinary):
|
||||||
return False
|
# if observation.shape == (observation_space.n,):
|
||||||
elif len(observation.shape) == 2 and observation.shape[1] == observation_space.n:
|
# return False
|
||||||
return True
|
# elif len(observation.shape) == 2 and observation.shape[1] == observation_space.n:
|
||||||
else:
|
# return True
|
||||||
raise ValueError("Error: Unexpected observation shape {} for MultiBinary ".format(observation.shape) +
|
# else:
|
||||||
"environment, please use ({},) or ".format(observation_space.n) +
|
# raise ValueError("Error: Unexpected observation shape {} for MultiBinary ".format(observation.shape) +
|
||||||
"(n_env, {}) for the observation shape.".format(observation_space.n))
|
# "environment, please use ({},) or ".format(observation_space.n) +
|
||||||
|
# "(n_env, {}) for the observation shape.".format(observation_space.n))
|
||||||
else:
|
else:
|
||||||
raise ValueError("Error: Cannot determine if the observation is vectorized with the space type {}."
|
raise ValueError("Error: Cannot determine if the observation is vectorized with the space type {}."
|
||||||
.format(observation_space))
|
.format(observation_space))
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue