Skip to content

Commit 897cfd0

Browse files
Bold the heading
Co-authored-by: amanda-butler-unity <[email protected]>
1 parent 18b07eb commit 897cfd0

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

com.unity.ml-agents/Documentation~/Training-ML-Agents.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -558,7 +558,7 @@ Each `Lesson` has 3 fields :
558558
| `min_lesson_length` | The minimum number of episodes that should be completed before the lesson can change. If `measure` is set to `reward`, the average cumulative reward of the last `min_lesson_length` episodes will be used to determine if the lesson should change. Must be nonnegative. <br><br> **Important**: the average reward that is compared to the thresholds is different than the mean reward that is logged to the console. For example, if `min_lesson_length` is `100`, the lesson will increment after the average cumulative reward of the last `100` episodes exceeds the current threshold. The mean reward logged to the console is dictated by the `summary_freq` parameter defined above. |
559559
| `signal_smoothing` | Whether to weight the current progress measure by previous values. |
560560
| `require_reset` | Whether changing lesson requires the environment to reset (default: false) |
561-
##### Training with a Curriculum
561+
**Training with a Curriculum**
562562

563563
Once we have specified our metacurriculum and curricula, we can launch
564564
`mlagents-learn` to point to the config file containing

0 commit comments

Comments
 (0)