Back to Search
E

Eureka

Modelactive

NVIDIA model using LLMs for automatic reward function design in robot RL.

Details

Updated:6/21/2026
open sourcetrue
release date2023-10-19
github urlhttps://github.com/eureka-research/Eureka
paper urlhttps://arxiv.org/abs/2310.12931
model familyEureka

Tags

reward-designLLMreinforcement-learningnvidiaICLR-2024code-generationGPT-4

Relationships

Sources

https://arxiv.org/abs/2310.12931
paper
Visit
https://github.com/eureka-research/Eureka
github
Visit

Related Knowledge Pages

No related knowledge pages.