ERFSL generates and optimizes LLM-based reward functions for custom multi-objective RL, correcting codes in one iteration and converging weights in 5.2 iterations on average even from 500x errors.
Large language models as evolutionary optimizers,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ERFSL uses LLMs to create per-requirement reward components, correct their code via a critic, and optimize weights with genetic-algorithm-style mutation and crossover driven by training logs, succeeding in a zero-shot data collection task.
citing papers explorer
-
ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract)
ERFSL generates and optimizes LLM-based reward functions for custom multi-objective RL, correcting codes in one iteration and converging weights in 5.2 iterations on average even from 500x errors.
-
Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement
ERFSL uses LLMs to create per-requirement reward components, correct their code via a critic, and optimize weights with genetic-algorithm-style mutation and crossover driven by training logs, succeeding in a zero-shot data collection task.