-
It looks like still a alphazero, can you Implementing muzero in go game?
-
I notice that your implementation of Gumbel MuZero has two differences with the original algorithm.
1. The gumbel_scale is fixed to 10.0, while mctx uses 1.0 or 0.0 (only in evaluation).
2. Dirich…
-
I found the time cost use method muzero_policy is much longer than gumbel_muzero_policy in same num_simulations, roughly three times as much. is this normal? and why?
-
when running:
python3 ./zoo/box2d/lunarlander/config/lunarlander_disc_gumbel_muzero_config.py
It will pop out the following error:
File "/home/1project/LightZero-main/lzero/policy/gumbel_muze…
-
Would you consider adding support for [JAX](https://github.com/google/jax)?
-
In alzero paper, the elo of go is exceed 5000, but in Gumbel paper, the elo of go is below 3000. why?
if a agent training use num_simulations==800, then i continue train use num_simulations==40…
-
When trying to run gumbel_muzero:
python3 ./zoo/board_games/tictactoe/config/tictactoe_gumbel_muzero_bot_mode_config.py
on the main branch, this error pop out.
And it seems that there's no 'gumbe…
-
for any game which set the "action_mask" not equal all 1, for example when creating the BaseEnv:
if not self._continuous:
action_mask = np.ones(self.discrete_action_num, 'int8'…
-
Hello,
I have a question about the [`qtransform_by_parent_and_siblings`](https://github.com/google-deepmind/mctx/blob/main/mctx/_src/qtransforms.py#L53-L84) function [used in `muzero_policy` as def…
-
Hello,
I hope this message finds you well. I am reaching out to kindly request the addition of a link to my project, [Pgx](http://github.com/sotetsuk/pgx), in the README file of the Mctx repository…