-
I've seen others reporting that the `muzero_policy` is slow and I've run into this problem myself so I wanted to add a bit more information. I'm not expecting a solution to this problem, but it might …
-
Hello all! Thank you for creating mctx for the community. I added a performance enhancement to my copy of mctx and am wondering if you're interested in adding it to the official repo.
Computing bot…
-
This library contains implementations of
- [Gumbel MuZero](https://openreview.net/forum?id=bERaNdoegnO) (policy improvement)
- [Stochastic MuZero](https://openreview.net/forum?id=X6D9bAHhBQ1) (cha…
-
We have read the docs carefully. However, we cannot find such example. All we can find is:
https://github.com/opendilab/LightZero/blob/main/docs/source/tutorials/envs/customize_envs_zh.md
What w…
-
Hi,
I'd like to ask about how to make minatar environments deterministic for research on MBRL algorithms such as MuZero, which are designed for deterministic environments.
Apart from setting th…
-
Example:
```python3
import jax
import mctx
from jax import numpy as jnp, random
def main():
n_actions = 7
n_outcomes = 3
batch_size = 1
root = mctx.RootFnOutput( # ty…
-
Would you consider adding support for [JAX](https://github.com/google/jax)?
-
While running
python3 ./zoo/game_2048/config/stochastic_muzero_2048_config.py
It will pop out some error in GameSegment at line 171:
assert len(next_segment_observations)
-
I'm trying to adapt the tutorial code to my environment which has the following dimensions:
```
env.observation_space.shape[0] #Continuous
50
```
```
env.action_space.n #Discrete
3
```
I'm …
-
It is possible to automatically determine the `num_actions` and `num_chance_outcomes` parameters to [`stochastic_muzero_policy`](https://github.com/google-deepmind/mctx/blob/main/mctx/_src/policies.py…