PoliFormer: Scaling On-Policy RL with Transformers

POLIFORMER is a transformer-based policy model trained with on-policy RL in the AI2-THOR simulator at scale, that can effectively navigate in the real world without any adaptation.

Data and Resources

Cite this as

Kuo-Hao Zeng, Zichen Zhang, Kiana Ehsani, Rose Hendrix, Jordi Salvador, Alvaro Herrasti, Ross Girshick, Aniruddha Kembhavi, Luca Weihs (2024). Dataset: PoliFormer: Scaling On-Policy RL with Transformers. https://doi.org/10.57702/avmh5rc8

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Kuo-Hao Zeng
More Authors
Zichen Zhang
Kiana Ehsani
Rose Hendrix
Jordi Salvador
Alvaro Herrasti
Ross Girshick
Aniruddha Kembhavi
Luca Weihs
Homepage https://poliformer.allen.ai