Timeline for Difference between AlphaGo's policy network and value network
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 5, 2016 at 1:28 | history | edited | SmallChess | CC BY-SA 3.0 |
deleted 145 characters in body
|
| Apr 5, 2016 at 1:19 | comment | added | SmallChess | @Imran Feel free to edit my post. | |
| Apr 4, 2016 at 20:14 | comment | added | Imran | @StudentT Nice explanation of some of the key equations. I would make one small change: It doesn't make a lot of sense to say "You need to see ten moves ahead" to understand the position in Monte Carlo Tree Search. MCTS is a depth-first proof number search, and we don't really ever reach fixed depths like we would with iterative deepening in chess. Even with the value network allowing us evaluations of nodes before the end of the game, we are still not reaching these in a breadth first manner, and there is no min-max evaluation of the nodes, etc. | |
| Apr 4, 2016 at 13:52 | history | edited | SmallChess | CC BY-SA 3.0 |
deleted 4 characters in body
|
| Apr 2, 2016 at 22:36 | comment | added | SmallChess | @NeilSlater Ok. The networks aren ot perfect, but the reasons I have here are still good, just that we need more MC simulations. | |
| Apr 2, 2016 at 18:06 | comment | added | Neil Slater | I think this gives much deeper insight to the internal mechanisms. I am still not sure whether it explains why the two networks. The issue I have is "assume the evaluation network ... is perfect". If that was the case, then indeed the policy network is redundant. Just look one move ahead (for all possible moves) and pick the one with the best value network assessment. Of course the value network isn't perfect, and I suspect it gets more accurate the further progressed into the game . . . but I don't know how true/useful that is, or whether it completes this answer. | |
| Apr 2, 2016 at 10:57 | history | edited | SmallChess | CC BY-SA 3.0 |
edited body
|
| Apr 2, 2016 at 10:52 | history | edited | SmallChess | CC BY-SA 3.0 |
edited body
|
| Apr 2, 2016 at 10:47 | history | answered | SmallChess | CC BY-SA 3.0 |