-
Hi Daniel,
I'm trying to run a custom environment (works with muzero) with your Stochastic-muzero version.
After creating a config file (just changing env name in experiment_450_config.json) I'm…
-
Thanks for releasing this library!!
In the Gumbel MuZero paper (appendix F), I read:
![image](https://user-images.githubusercontent.com/16518885/214013465-4f15ec1f-403d-4bd3-a882-b1197958df5b.p…
-
Hello!
I'm trying to use `mctx` library to train MuZero agent and have some troubles with understanding `RootFnOutput`.
I have two methods `.root` and `.recurrent`:
```python
def root(
…
-
Hi, thanks for open sourcing the great library!
I'm using it to experiment with MCTS on a project, and I have a question regarding the function \sigma used in constructing the improved policy: \pi'…
-
Hi Daniel,
I'm running the experiment_450_config.json without modifications with this command:
```
python muzero_cli.py train report config/experiment_450_config.json
```
And I'm getting th…
-
Hello! Thank you for recently adding an implementation of stochastic muzero. I was testing it, but it seems chance outcome and action outputs within the search are irregular. I made this test and prin…
-
Just an idea.
https://github.com/deepmind/mctx
ipsec updated
2 years ago
-
Recently, I finished reading this repo code. And I found that the entropy bonus of a state value from SAC is only added at the last output step.
This routine let me can't help but thinking:
If t…
-
Erre kíváncsi lennék:
Exploring Weight Agnostic Neural Networks
Tuesday, August 27, 2019
Posted by Adam Gaier, Student Researcher and David Ha, Staff Research Scientist, Google Research, Tokyo
…
-
As muzero implies that it is only suitable for deterministic game, does it mean that using original muzero would produce worse result than that from classic model-free algo in nondeterministic game?
…