mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-19 10:00:55 +00:00
Update examples.rst (#1969)
This commit is contained in:
parent
d8148deeaa
commit
1a69fc8314
1 changed files with 3 additions and 3 deletions
|
|
@ -179,9 +179,9 @@ Multiprocessing with off-policy algorithms
|
||||||
|
|
||||||
vec_env = make_vec_env("Pendulum-v0", n_envs=4, seed=0)
|
vec_env = make_vec_env("Pendulum-v0", n_envs=4, seed=0)
|
||||||
|
|
||||||
# We collect 4 transitions per call to `ènv.step()`
|
# We collect 4 transitions per call to `env.step()`
|
||||||
# and performs 2 gradient steps per call to `ènv.step()`
|
# and performs 2 gradient steps per call to `env.step()`
|
||||||
# if gradient_steps=-1, then we would do 4 gradients steps per call to `ènv.step()`
|
# if gradient_steps=-1, then we would do 4 gradients steps per call to `env.step()`
|
||||||
model = SAC("MlpPolicy", vec_env, train_freq=1, gradient_steps=2, verbose=1)
|
model = SAC("MlpPolicy", vec_env, train_freq=1, gradient_steps=2, verbose=1)
|
||||||
model.learn(total_timesteps=10_000)
|
model.learn(total_timesteps=10_000)
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue