Stanford-ILIAD/ELLA
Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.
Python
Stargazers
- AlexandrParkhomenkoNN
- denisfitz57
- DilipA
- dyabelTsinghua University
- fly51flyPRIS
- frankroederTUHH
- GilgameshDNVIDIA
- jayelmStanford University
- junsu-kim97KAIST
- lakshitadodeja
- Near32
- oceankUniversity of South Carolina
- SlyJabiru
- TheodoreGalanosAustrian Institute of Technology
- valaxkong
- YinpeiDaiComputer Science
- yipliuHunan University