search

instadeepai / jumanji

🕹️ A diverse suite of scalable reinforcement learning environments in JAX
https://instadeepai.github.io/jumanji
Apache License 2.0
645 stars 80 forks source link

The problem with graph coloring #237

Closed Wendyuf closed 7 months ago

Wendyuf commented 7 months ago

I was wondering the performance shown in the paper related to graph coloring. It seems it stucked in local minimum?

clement-bonnet commented 7 months ago

Hi @Wendyuf, the optimal return for GraphColoring is not known. Therefore, it is not easy to judge the expected quality of the solution by simply looking at the return. Rendering a few episodes or checking training the agent on a few well-known instances might help characterize its performance. Hope this helps!

clement-bonnet commented 7 months ago

I hope this answers your question! I'm going to close this for now but feel free to reopen if anything is unclear. Thanks.