Implementation of the RLHF-based reward learning algorithm T-REX (https://arxiv.org/pdf/1904.06387.pdf).
adityakuppa26/T-REX
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
| Name | Name | Last commit date | ||
|---|---|---|---|---|
Implementation of the RLHF-based reward learning algorithm T-REX (https://arxiv.org/pdf/1904.06387.pdf).