蒲源

Hi, One more question about runtime. In the EfficientZero paper A.5 evaluation, the paper states that "To train an Atari agent for 100k steps, it only needs 4 GPUs to...

> Hello I'm trying to adapt the code for the single-player game like 2048 but it seems that I got RecursionError often and if I set sys.sys.setrecursionlimit(...). The program may...

Hello, thank you to the contributors for their outstanding work on this repository. Regarding the issue you've raised, you might be interested in the project "[LightZero: A Unified Benchmark for...

Hello, thank you to the contributors for their outstanding work on this repository. Regarding the issue you've raised, you might be interested in the project "[LightZero: A Unified Benchmark for...

Hello, thank you to the contributors for their outstanding work on this repository. Regarding the issue you've raised, you might be interested in the project "[LightZero: A Unified Benchmark for...

Hello! Regarding the support on the Go environment, we have been working on this PR (https://github.com/opendilab/LightZero/pull/65/files) for a while. This PR includes the initial implementation of the regular self-play version...

To effectively model this game environment and train an agent to maximize the value of gold nuggets obtained from a 10x10 grid, you can take the following steps: ### 1....

Hello! According to your description, first please confirm: is the episode length fixed at 5 steps? If MuZero is performing poorly and there's no issue with the environment part you've...

Hello, I recommend starting by adjusting MuZero rather than EfficientZero, as the latter adds complexity, particularly in predicting the value prefix, which may not be advantageous in your environment. To...

Hello, the action space is fixed at 100, which is considerably smaller compared to the maximum action space of 19*19 in Go. Therefore, theoretically, MuZero should manage this scale effectively....