mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-18 21:30:19 +00:00
5143cd19f7
* fix Atari in CI * fix dtype and atari extra * Update setup.py * remove 3.6 * note about how to install Atari * pendulum-v1 * atari v5 * black * fix pendulum capitalization * add minimum version * moved things in changelog to breaking changes * partial v5 fix * env update to pass tests * mismatch env version fixed * Fix tests after merge * Include autorom in setup.py * Blacken code * Fix dtype issue in more robust way * Fix GitLab CI: switch to Docker container with new black version * Remove workaround from GitLab. (May need to rebuild Docker for this though.) * Revert to v4 * Update setup.py * Apply suggestions from code review * Remove unnecessary autorom * Consistent gym versions Co-authored-by: J K Terry <justinkterry@gmail.com> Co-authored-by: Anssi <kaneran21@hotmail.com> Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> Co-authored-by: modanesh <mohamad4danesh@gmail.com> Co-authored-by: Adam Gleave <adam@gleave.me>
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
import pytest
|
|
import torch as th
|
|
|
|
from stable_baselines3 import A2C, DQN, PPO, SAC, TD3
|
|
from stable_baselines3.common.sb2_compat.rmsprop_tf_like import RMSpropTFLike
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"net_arch",
|
|
[
|
|
[12, dict(vf=[16], pi=[8])],
|
|
[4],
|
|
[],
|
|
[4, 4],
|
|
[12, dict(vf=[8, 4], pi=[8])],
|
|
[12, dict(vf=[8], pi=[8, 4])],
|
|
[12, dict(pi=[8])],
|
|
],
|
|
)
|
|
@pytest.mark.parametrize("model_class", [A2C, PPO])
|
|
def test_flexible_mlp(model_class, net_arch):
|
|
_ = model_class("MlpPolicy", "CartPole-v1", policy_kwargs=dict(net_arch=net_arch), n_steps=64).learn(300)
|
|
|
|
|
|
@pytest.mark.parametrize("net_arch", [[], [4], [4, 4], dict(qf=[8], pi=[8, 4])])
|
|
@pytest.mark.parametrize("model_class", [SAC, TD3])
|
|
def test_custom_offpolicy(model_class, net_arch):
|
|
_ = model_class("MlpPolicy", "Pendulum-v1", policy_kwargs=dict(net_arch=net_arch), learning_starts=100).learn(300)
|
|
|
|
|
|
@pytest.mark.parametrize("model_class", [A2C, PPO, SAC, TD3])
|
|
@pytest.mark.parametrize("optimizer_kwargs", [None, dict(weight_decay=0.0)])
|
|
def test_custom_optimizer(model_class, optimizer_kwargs):
|
|
kwargs = {}
|
|
if model_class in {DQN, SAC, TD3}:
|
|
kwargs = dict(learning_starts=100)
|
|
elif model_class in {A2C, PPO}:
|
|
kwargs = dict(n_steps=64)
|
|
|
|
policy_kwargs = dict(optimizer_class=th.optim.AdamW, optimizer_kwargs=optimizer_kwargs, net_arch=[32])
|
|
_ = model_class("MlpPolicy", "Pendulum-v1", policy_kwargs=policy_kwargs, **kwargs).learn(300)
|
|
|
|
|
|
def test_tf_like_rmsprop_optimizer():
|
|
policy_kwargs = dict(optimizer_class=RMSpropTFLike, net_arch=[32])
|
|
_ = A2C("MlpPolicy", "Pendulum-v1", policy_kwargs=policy_kwargs).learn(500)
|
|
|
|
|
|
def test_dqn_custom_policy():
|
|
policy_kwargs = dict(optimizer_class=RMSpropTFLike, net_arch=[32])
|
|
_ = DQN("MlpPolicy", "CartPole-v1", policy_kwargs=policy_kwargs, learning_starts=100).learn(300)
|