IliaLarchenko/dot_transfer_cube
Robotics
•
Updated
•
22
Ilia Larchenko PRO
IliaLarchenko
AI & ML interests
I am a Data Science Director with a diverse technical and business background. I live in Bangkok and work in Agoda, where I lead multiple DS and ML teams. I was an active Kaggler in TOP-20 of a global competition ranking, Competitions and Notebooks Master
Recent Activity
published
a model
29 days ago
IliaLarchenko/dot_transfer_cube
updated
a model
29 days ago
IliaLarchenko/dot_transfer_cube
new activity
29 days ago
lerobot/act_aloha_sim_insertion_human:Should episode_length be increased to 500?
Organizations
IliaLarchenko's activity
published
a
model
29 days ago
updated
a
model
29 days ago
Should episode_length be increased to 500?
#1 opened 29 days ago
by
IliaLarchenko
updated
4
models
about 1 month ago
posted
an
update
about 1 month ago
Post
2096
I am presenting Decoder-Only Transformer (DOT) Policy a simple Behavioral Control policy that outperforms SOTA models on two simple benchmark tasks:
✅ PushT (pushing an object to a goal) – 84% success on keypoints, 74% on images (previous best: 75% / 69%)
✅ ALOHA Insert (precise bimanual insertion) – 30% success (previous best: ~21%)
The best part? DOT is much smaller (sometimes 100 times less parameters) than previous SOTA models, trains faster, and avoids complexity:
🚫 No generative models (Diffusion, VAE, GANs)
🚫 No discretization/tokenization of actions
🚫 No reinforcement learning or multi-stage training
✅ Just learns from human demos, plain and simple
This is still early — more complex real-life tasks need testing, and no guarantees it will actually work well there, but I think it's interesting to share. Sometimes, simpler approaches can be just as effective (or even better) than complex ones.
🔗 Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy
Trained models on Hugging Face:
IliaLarchenko/dot_pusht_keypoints
IliaLarchenko/dot_pusht_images
IliaLarchenko/dot_bimanual_insert
✅ PushT (pushing an object to a goal) – 84% success on keypoints, 74% on images (previous best: 75% / 69%)
✅ ALOHA Insert (precise bimanual insertion) – 30% success (previous best: ~21%)
The best part? DOT is much smaller (sometimes 100 times less parameters) than previous SOTA models, trains faster, and avoids complexity:
🚫 No generative models (Diffusion, VAE, GANs)
🚫 No discretization/tokenization of actions
🚫 No reinforcement learning or multi-stage training
✅ Just learns from human demos, plain and simple
This is still early — more complex real-life tasks need testing, and no guarantees it will actually work well there, but I think it's interesting to share. Sometimes, simpler approaches can be just as effective (or even better) than complex ones.
🔗 Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy
Trained models on Hugging Face:
IliaLarchenko/dot_pusht_keypoints
IliaLarchenko/dot_pusht_images
IliaLarchenko/dot_bimanual_insert
Incorrect dataset
#2 opened about 1 month ago
by
IliaLarchenko
published
4
models
about 1 month ago
updated
4
models
about 1 month ago