teach icon indicating copy to clipboard operation
teach copied to clipboard

TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.

Results 14 teach issues
Sort by recently updated
recently updated
newest added

Bumps [pydantic](https://github.com/pydantic/pydantic) from 1.8.2 to 1.10.13. Release notes Sourced from pydantic's releases. V1.10.13 2023-09-27 What's Changed Update pip commands to install 1.10 by @​chbndrhnns in pydantic/pydantic#6930 Make the v1 mypy...

dependencies

May I ask what the inputs and outputs of this model are? In my understanding, visual language navigation tasks should not be able to provide input for language and visual...

When I run ** sudo python ./bin/startx.py**,I will meet that > Starting X on DISPLAY=:0 Traceback (most recent call last): File "./bin/startx.py", line 108, in main() File "./bin/startx.py", line 104,...

Hello, We have found a problem with interaction when attempting to place many objects on the same plate or bowl. We have found that when one or more object (e.g.,...

Hello everyone, thanks for the contribution of the benchmark! Is there any chance to run this from within a docker container (as our infrastructure requires to do so)? We run...

Hi, I noticed that the `data.vocab` stored in the baseline model has a different vocabulary length compared to the language embedding stored in pretrained model. For the baseline model "et_plus_h",...

Hi, I ran the baseline ET model and found that two different runs get significantly different evaluation metrics. (might relate to this issue #10) Run1: ``` SR: 77/608 = 0.127...

Hi @aishwaryap, Thank you for releasing the dataset. It seems that there is a bug in the `get_state_changes` function: https://github.com/alexa/teach/blob/5554f02f55c22abfe5c2a749dbb24c13377726c8/src/teach/utils.py#L92 I believe it should be `agent_final = final_state["agents"][idx] ` instead....

README.md states that only python version >=3.7 and =3.7. Is Python 3.9 officially supported?

Hi @aishwaryap, I was reading about the recent changes to the code reported in #10 and we unfortunately get results that differ substantially from yours. I started dissecting the code...