gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-08-01 14:10:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update vector_envs_tutorial.py (#1133)

Browse Source
This commit is contained in:
Chen Tao
2024-08-05 17:18:21 +08:00
committed by GitHub
parent a576025834
commit 4a85589b92
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/tutorials/gymnasium_basics/vector_envs_tutorial.py
View File

@@ -417,7 +417,7 @@ agent = A2C(obs_shape, action_shape, device, critic_lr, actor_lr, n_envs)
# For our training loop, we are using the `RecordEpisodeStatistics` wrapper to record the episode lengths and returns and we are also saving
# the losses and entropies to plot them after the agent finished training.
#
# You may notice that the don't reset the vectorized envs at the start of each episode like we would usually do.
# You may notice that we don't reset the vectorized envs at the start of each episode like we would usually do.
# This is because each environment resets automatically once the episode finishes (each environment takes a different number of timesteps to finish
# an episode because of the random seeds). As a result, we are also not collecting data in `episodes`, but rather just play a certain number of steps
# (`n_steps_per_update`) in each environment (as an example, this could mean that we play 20 timesteps to finish an episode and then