Eureka uses LLMs for evolutionary optimization of reward code to outperform human experts on 83% of 29 RL tasks with 52% average improvement and enables gradient-free RLHF.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2023 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Eureka: Human-Level Reward Design via Coding Large Language Models
Eureka uses LLMs for evolutionary optimization of reward code to outperform human experts on 83% of 29 RL tasks with 52% average improvement and enables gradient-free RLHF.