-
This issue appears only in the implementation of continuous actions version of MuZero.
When computing child visits, we need to divide by sum_visits in order to be in probabilities form.
But, it …
-
## 🚀 Feature
Support for Multi-Categorical in torch.distributions
## Motivation
As openai gym supports ``MultiDiscrete`` space, it would be nice if pytorch can support the corresponding…
-
Any suggestions for changing the code such that we can adopt it for single player game in which the rules are available and the goal is to get the highest score? For example, `snake eating egg` game a…
-
Hello,
I am trying to reproduce the result of Muzero on Atari (I am using the MsPacmanNoFrameskip-v4 env as it's the one with the most published result on the original paper of [Muzero](https://arx…
-
### Question
Hi, I would like to know if Gymnasium supports the functionality of simulating actions in a given state. For example, the agent is in a state and wants to perform a simulation five steps…
-
It would be nice to add the following algorithms:
- [ ] RAINBOW
- [x] A2C (multiprocessing)
I will submit a PR if I finish any of them.
-
I would like to request Royal Game of Ur environment for Pgx. Royal Game of Ur is a simple race game with chance and perfect information but it has some distinct features.
First, it might be an old…
-
### Description
I've got a self-play (not important) function that I would like to execute on the CPU, but I'm running into an issue where the execution mysteriously freezes on the 32nd iteration. No…
-
- Cum Laude candidate
[USA House of Representatives - INVESTIGATION OF COMPETITION IN DIGITAL MARKETS ](https://www.govinfo.gov/content/pkg/CPRT-117HPRT47832/pdf/CPRT-117HPRT47832.pdf) :
```
As p…
-
I was looking at the implementation of the minigrid environment as inspiration to create my own environment. I noticed that the correspoin efficient muzero config doesnt actually use the environment. …