AlphaZeroSimple
AlphaZeroSimple copied to clipboard
JoshVarty
The absolute most basic example of AlphaZero and Monte Carlo Tree Search I could come up with
https://github.com/JoshVarty/AlphaZeroSimple/blob/b68171a5cb9367b407017e07f5de3f65b10e888e/trainer.py#L83,L85
1/500 Traceback (most recent call last): File "main.py", line 27, in trainer.learn() File "/home/uu/decy5/inne_nz/AlphaZeroSimple/trainer.py", line 61, in learn self.train(train_examples) File "/home/uu/decy5/inne_nz/AlphaZeroSimple/trainer.py", line 83, in train boards = boards.contiguous().cuda() File "/home/uu/.local/lib/python3.8/site-packages/torch/cuda/__init__.py",...
We don't need to make the Monte Carlo Search Tree object live inside of the trainer. It can exist as a local inside `execute_episode()`.
I've misnamed this function. It should be called `Backup()`. See: https://www.nature.com/articles/nature24270.epdf?author_access_token=VJXbVjaSHxFoctQQ4p2k4tRgN0jAjWel9jnR3ZoTv0PVW4gB86EEpGqTRDtpIz-2rmo8-KG06gqVobU5NSCFeHILHcVFUeMsbvwS-lxjqQGg98faovwjxeTUgZAUMnRQ
Hey, First of all thanks for the video, post, and the code. I really find it underrated as I went over almost every single resource on AZ. I am still...
Changed the backpropagate() function in monte_carlo_tree_search.py to backup() and removed the torch import as it was unused import in this python file
In your [blog](https://joshvarty.github.io/AlphaZero/), you emphasize "We record the **state** and the **probabilities produced by the MCTS**" Do you mean we record board state, priors and values? [Trainer.exceute_episode](https://github.com/JoshVarty/AlphaZeroSimple/blob/master/trainer.py#L45) `ret.append((hist_state, hist_action_probs, reward...
Hi Josh, In order to better understand the code, I tested it with plain pytorch without CUDA but it failed with `AssertionError: Torch not compiled with CUDA enabled` from `File...
Hi there, I found your project on youtube and it is such a good explanation of the alpha zero algorithm. Thank you very much for that! :) I was wondering...
