mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-16 21:10:08 +00:00
18d10dbf42
* Update evaluate_policy to use monitor data if available * Update documentation * Cleaning up * Remove unnecessary typing trickery * Update doc * Rename is_wrapped to clarify it is for vecenvs * Add is_wrapped for regular envs * Add is_wrapped call for subprocvecenv and update code for circular imports * Move new functions back to env_util and fix imports * Update changelog * Clarify evaluate_policy docs * Add tests for wrapped modifying episode lengths * Fix tests * Update changelog * Minor edits * Add warn switch to evaluate_policy and update tests Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
48 lines
1.8 KiB
Python
48 lines
1.8 KiB
Python
import numpy as np
|
|
import pytest
|
|
|
|
from stable_baselines3 import A2C, DDPG, DQN, PPO, SAC, TD3
|
|
from stable_baselines3.common.evaluation import evaluate_policy
|
|
from stable_baselines3.common.identity_env import IdentityEnv, IdentityEnvBox, IdentityEnvMultiBinary, IdentityEnvMultiDiscrete
|
|
from stable_baselines3.common.noise import NormalActionNoise
|
|
from stable_baselines3.common.vec_env import DummyVecEnv
|
|
|
|
DIM = 4
|
|
|
|
|
|
@pytest.mark.parametrize("model_class", [A2C, PPO, DQN])
|
|
@pytest.mark.parametrize("env", [IdentityEnv(DIM), IdentityEnvMultiDiscrete(DIM), IdentityEnvMultiBinary(DIM)])
|
|
def test_discrete(model_class, env):
|
|
env_ = DummyVecEnv([lambda: env])
|
|
kwargs = {}
|
|
n_steps = 3000
|
|
if model_class == DQN:
|
|
kwargs = dict(learning_starts=0)
|
|
n_steps = 4000
|
|
# DQN only support discrete actions
|
|
if isinstance(env, (IdentityEnvMultiDiscrete, IdentityEnvMultiBinary)):
|
|
return
|
|
|
|
model = model_class("MlpPolicy", env_, gamma=0.4, seed=1, **kwargs).learn(n_steps)
|
|
|
|
evaluate_policy(model, env_, n_eval_episodes=20, reward_threshold=90, warn=False)
|
|
obs = env.reset()
|
|
|
|
assert np.shape(model.predict(obs)[0]) == np.shape(obs)
|
|
|
|
|
|
@pytest.mark.parametrize("model_class", [A2C, PPO, SAC, DDPG, TD3])
|
|
def test_continuous(model_class):
|
|
env = IdentityEnvBox(eps=0.5)
|
|
|
|
n_steps = {A2C: 3500, PPO: 3000, SAC: 700, TD3: 500, DDPG: 500}[model_class]
|
|
|
|
kwargs = dict(policy_kwargs=dict(net_arch=[64, 64]), seed=0, gamma=0.95)
|
|
if model_class in [TD3]:
|
|
n_actions = 1
|
|
action_noise = NormalActionNoise(mean=np.zeros(n_actions), sigma=0.1 * np.ones(n_actions))
|
|
kwargs["action_noise"] = action_noise
|
|
|
|
model = model_class("MlpPolicy", env, **kwargs).learn(n_steps)
|
|
|
|
evaluate_policy(model, env, n_eval_episodes=20, reward_threshold=90, warn=False)
|