Closed StOnEGiggity closed 3 years ago
@StOnEGiggity the seq2seq training uses a static dataset to train the models in an offline fashion. If you are interested in using additional info from the simulator you have two options:
augment_trajectories.py
to replay all the trajectories in the dataset, save additional info about objects etc., then train models offline with the augmented dataset.eval_seq2seq.py
for online interactions. Currently eval_seq2seq.py
takes a pre-trained model and evaluates it interactively with the simulator (with navigation and manipulation). You will need to modify it to your needs.Are there plans to support the latest AI2Thor version 2.7.4? It seems that it speeds up rendering which could make it practical to apply (sample-inefficient) RL algorithms directly in the environment. I am new to both AI2Thor and ALFRED, but if you are aware of the changes needed to support the latest version, I could try to implement them myself
Hi @ankit61, this pull request thread might be relevant: https://github.com/askforalfred/alfred/pull/45
Unfortunately minor changes in the scene layouts between 2.1.0 and 2.7.4 would invalidate some referring expressions and instructions in the dataset. But nonetheless you can pre-train an agent in 2.7.4 to learn robust visual representations and possibly finetune it with language data in 2.1.0.
Closing due to inactivity.
Hi,
I have one question here. Is that possible to navigate directly in Ai2-Thor environment? I notice training data includes discrete vision features. I want to directly run Ai2-Thor environment and obtain the status of the interactive objects from API.
I am new to AI2-thor and ALFRED. If I make some misunderstanding about AI2-Thor and ALFRED, please point out my mistakes.
Thanks a lot.