2019-09-26 09:46:40 +00:00
|
|
|
.. _quickstart:
|
|
|
|
|
|
|
|
|
|
===============
|
|
|
|
|
Getting Started
|
|
|
|
|
===============
|
|
|
|
|
|
|
|
|
|
Most of the library tries to follow a sklearn-like syntax for the Reinforcement Learning algorithms.
|
|
|
|
|
|
|
|
|
|
Here is a quick example of how to train and run SAC on a Pendulum environment:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
import gym
|
|
|
|
|
|
|
|
|
|
from torchy_baselines.sac.policies import MlpPolicy
|
|
|
|
|
from torchy_baselines.common.vec_env import DummyVecEnv
|
|
|
|
|
from torchy_baselines import SAC
|
|
|
|
|
|
2020-01-20 15:19:35 +00:00
|
|
|
env = gym.make('Pendulum-v0')
|
2019-09-26 09:46:40 +00:00
|
|
|
|
|
|
|
|
model = SAC(MlpPolicy, env, verbose=1)
|
|
|
|
|
model.learn(total_timesteps=10000)
|
|
|
|
|
|
|
|
|
|
obs = env.reset()
|
|
|
|
|
for i in range(1000):
|
|
|
|
|
action = model.predict(obs)
|
|
|
|
|
obs, rewards, dones, info = env.step(action)
|
|
|
|
|
env.render()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Or just train a model with a one liner if
|
|
|
|
|
`the environment is registered in Gym <https://github.com/openai/gym/wiki/Environments>`_ and if
|
|
|
|
|
the policy is registered:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
from torchy_baselines import SAC
|
|
|
|
|
|
|
|
|
|
model = SAC('MlpPolicy', 'Pendulum-v0').learn(10000)
|
