Training with ddppo_pick.yaml doesn't converge

[RealZiangLiu]

Habitat-Lab and Habitat-Sim versions

Habitat-Lab: hab_suite

Habitat-Sim: master

Habitat is under active development, and we advise users to restrict themselves to stable releases. Are you using the latest release versions of Habitat-Lab and Habitat-Sim? Your question may already be addressed in the latest versions. We may also not be able to help with problems in earlier versions because they sometimes lack the more verbose logging needed for debugging.

Master branch contains 'bleeding edge' code and should be used at your own risk.

Docs and Tutorials

Did you read the docs? https://aihabitat.org/docs/habitat-lab/

Did you check out the tutorials? https://aihabitat.org/tutorial/2020/

Perhaps your question is answered there. If not, carry on!

❓ Questions and Help

Hi, I tried training with the configs specified in ddppo_pick.yaml in an attempt to replicate the results in the Habitat 2.0 paper, but the model doesn't seem to converge within 100M steps as specified in the paper (with did_pick_object and rearrange_success being 0). Is there anything specific that I'll need to modify in the config to make it work? Thanks in advance.

[aclegg3]

@ziangliuusc,

We merged some changes recently and more are coming. Try again with current main and better yet, keep an eye out for our upcoming stable version release.