Commit
•
0347d5d
1
Parent(s):
0febb3e
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,14 +20,16 @@ Generate synthetic data set for the state that you want, search over the action
|
|
| 20 |
You can bootstrap process with priors still search for the desired state
|
| 21 |
|
| 22 |
|
| 23 |
-
|
| 24 |
Reward any trajectory proportionally to a semantically similar state as any state in a run with a victory condition.
|
| 25 |
Linear or some function reward curve
|
| 26 |
|
| 27 |
|
| 28 |
-
|
| 29 |
Sections of states with more changes in them
|
| 30 |
|
|
|
|
|
|
|
| 31 |
|
| 32 |
|
| 33 |
# 7/21/23
|
|
|
|
| 20 |
You can bootstrap process with priors still search for the desired state
|
| 21 |
|
| 22 |
|
| 23 |
+
## reward
|
| 24 |
Reward any trajectory proportionally to a semantically similar state as any state in a run with a victory condition.
|
| 25 |
Linear or some function reward curve
|
| 26 |
|
| 27 |
|
| 28 |
+
## Sample curve
|
| 29 |
Sections of states with more changes in them
|
| 30 |
|
| 31 |
+
## notes
|
| 32 |
+
http://www.incompleteideas.net/IncIdeas/BitterLesson.html
|
| 33 |
|
| 34 |
|
| 35 |
# 7/21/23
|