search

instadeepai / jumanji

🕹️ A diverse suite of scalable reinforcement learning environments in JAX
https://instadeepai.github.io/jumanji
Apache License 2.0
613 stars 78 forks source link

feat: updated checkpoint notebook to use checkpoints from hf model hub #166

Closed djbyrne closed 1 year ago

djbyrne commented 1 year ago

Checkpoints for all benchmarks can be found in InstaDeeps Model Hub page .

The naming convention is jumanji-[ENV-NAME]-[ENV-VERSION]-[MODEL]-[TYPE]

The checkpoint file has the naming convention [ENV-NAME]-[ENV-VERSION]_training_state Potentially it will be better to have a common training_state so that we can programatically pull down checkpoints?

CLAassistant commented 1 year ago

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

Donal Byrne seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
You have signed the CLA already but the status is still pending? Let us recheck it.

clement-bonnet commented 1 year ago

Closing this as a solution was found in #165