https://github.com/trigaten/tabular-q-learning_in_snake
https://github.com/trigaten/tabular-q-learning_in_snake
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/trigaten/tabular-q-learning_in_snake
- Owner: trigaten
- Created: 2020-03-04T02:33:51.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2022-05-06T00:59:11.000Z (over 3 years ago)
- Last Synced: 2025-02-05T15:43:53.638Z (8 months ago)
- Language: Python
- Size: 16 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Tabular-Q-Learning_In_Snake
Finds optimal policies for a given square game board.
https://user-images.githubusercontent.com/42948753/167049940-59e8cc8d-5bbd-45a0-9d28-5948c7178d4f.mov
--Run displayTest and change the line GAME_SIZE = to whatever boardsize you would like. Boardsizes > 3 will essentially not
compute because state spaces explode according to the following table (Actual section):
Possible states at a given board length, L
L | Upper Bound | Actual
1 : 1 | 1
2 : 236 | 44
3 : 137700 | 2080
4 : 535692272 | 143920
5 : 16475056294100 | 22073136