search

clvrai / spirl

Official implementation of "Accelerating Reinforcement Learning with Learned Skill Priors", Pertsch et al., CoRL 2020
186 stars 36 forks source link

completed_subtasks = info.pop("computed_tasks error") #21

Closed taewookim0812 closed 2 years ago

taewookim0812 commented 2 years ago

Hello, I have an issue on the SPiRL learning.

After I finished the skill prior learning on the kitchen environment, I tried to train the SPiRL_CL based on the skill prior network.

But I got the KeyError when my code attempts pop the key "completed_tasks" from info variable

image

I don't understand the code line 33 of __postprocessinfo because the returned "info" from step function only contains the following 5 key-value pairs as described in "kitchen_multitask_v0.py"

image

and, I could not find any other parts of adding the "completed_tasks" key to the info variable.

Am I missing something?

taewookim0812 commented 2 years ago

Sorry, I didn't check the same, but already closed issue. Now it works! and plz delete this issue.

Thanks anyway :)

kpertsch commented 2 years ago

Yes -- you need to install our fork of D4RL since we added a few info outputs to the env (to log subtask completion rates separately). Anyways, glad it works now, let me know if you have any other issues / questions! :)