Skip to content

keivalya/mini-wam

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

mini-WAM

(use with caution. this repo is still a work in progress)

A tiny World Action Model from scratch for robot learning.

mini-WAM extends the educational philosophy of mini-VLA.

Where mini-VLA learns:

image_t + language + state_t → action_t

mini-WAM learns:

image_t + language + state_t → action_t + state_t+1 + image_t+1

Why mini-WAM?

A VLA learns to act. A WAM learns to act while predicting what its action will do to the world.

Quickstart

pip install -r requirements.txt

python scripts/collect_data.py --env toy --num_episodes 100

python scripts/train.py \
  --env toy \
  --model_type wam \
  --action_head mlp \
  --predict_state \
  --device cpu

About

A tiny World Action Model from scratch for robot learning.

Topics

Resources

License

Stars

Watchers

Forks

Contributors

Languages