Timeline for When implementing Monte Carlo Tree Search for TicTacToe, do I simulate won states?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 2, 2018 at 2:33 | vote | accept | Amja | ||
| Aug 1, 2018 at 10:07 | history | edited | manlio | edited tags | |
| Aug 1, 2018 at 10:05 | answer | added | manlio | timeline score: 1 | |
| Dec 10, 2016 at 17:00 | comment | added | Amja | @CandiedOrange I understand that but I was wondering whether there was a difference between reaching a terminal state through random playout (not reflected in the game tree) vs through expansion of the tree. | |
| Dec 10, 2016 at 14:39 | comment | added | candied_orange | The game over states are the only states that give you a score in tic tac toe: win, lose, or draw. Back propogating that information is important. | |
| Dec 9, 2016 at 22:47 | review | First posts | |||
| Dec 12, 2016 at 11:18 | |||||
| Dec 9, 2016 at 22:46 | history | asked | Amja | CC BY-SA 3.0 |