-
I successfully trained a NN on my game for 8x8 and 12x12 boards. I am aiming at 16x16, which is the original board dimension.
Inference on a 8x8 board works perfectly, the NN seems to win against any…
-
Using CPU version
(CCZero) D:\象棋AI\ChineseChess-AlphaZero>python cchess_alphazero/run.py play
2022-07-20 02:46:43,360@cchess_alphazero.manager INFO # Config type: mini
pygame 2.1.2 (SDL 2.0.18, Pyt…
-
When I updated the jredis , I got the error when JRedisService reconnected .
The Exception info is as follow:
ERROR - -1 read count in readLine() while reading response line.
ERROR - PROBLEM: servi…
-
Hey all,
I am wondering how I can run the `benchmark/torch/AlphaZero` code. When I follow the instructions the code does not run out of the box. I would like to train a model and submit to Kaggle. …
-
See here: https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/
Not read yet...
-
https://www.researchgate.net/publication/331216459_Exact-Win_Strategy_for_Overcoming_AlphaZero
tl;dr Modified MCTS algorithm has a 61% winrate over the original (in 100 games) using the same networ…
-
The 10th training iteration for my game crashes with the following error.
This happens not only on my PC with a 16GB RTX3080 Laptop, but also on a cloud VM with a 40GB A100 GPU.
Could be related to …
-
Traceback (most recent call last):
File "play_games.py", line 43, in
File "cchess_alphazero\play_games\play.py", line 37, in start
File "cchess_alphazero\play_games\play.py", line 107, in st…
-
> The combination of Monte-Carlo tree search
(MCTS) with deep reinforcement learning has
led to significant advances in artificial intelligence. However, AlphaZero, the current stateof-the-art MCTS …
-
Hi! I just went over mcts.py. Here are few remarks:
- Great work :) this looks nice!
- The `MCTSNode` attributes `prior` and `policy` seems redundant: `node.prior = node.parent._policy['child_inde…