most citedVision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

6 citations · 6 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2024

ViSTa Dataset: Do vision-language models understand sequential tasks?

Evžen Wybitul, Evan Ryan Gunter, Mikhail Seleznyov +1

Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used…

cs.LG2023★ 6 cited

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Juan Rocamonde, Victoriano Montesinos, Elvis Nava +2

Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, whic…