generated from mwc/lab_tic_tac_toe
We did not code the computer to play tic-tac-toe due to us being told otherwise.
This commit is contained in:
12
notes.md
12
notes.md
@@ -38,9 +38,17 @@ and it's your turn, which action would you take? Why?
|
||||
---+---+--- ---+---+--- ---+---+--- ---+---+---
|
||||
| | | | O | | | |
|
||||
|
||||
1) Place X at the middle right to win
|
||||
|
||||
2) Place the X in the middle right again to block my opponent from winning
|
||||
|
||||
3) Place X at the top left of the board to gain an opportunity to win on the next turn
|
||||
|
||||
4) Place X in the middle for possible opportunities in the future and to block the opponents O in the top middle from being of any use.
|
||||
|
||||
### Initial game state
|
||||
|
||||
You can get the inital game state using game.get_initial_state().
|
||||
What is the current and future reward for this state? What does this mean?
|
||||
You can get the initial game state using `game.get_initial_state()`.
|
||||
Current reward is 0 so neither player has an advantage at the start.
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user