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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rocamonde, Juan, Montesinos, Victoriano, Nava, Elvis, Perez, Ethan, Lindner, David
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916159346966528
author Rocamonde, Juan
Montesinos, Victoriano
Nava, Elvis
Perez, Ethan
Lindner, David
author_facet Rocamonde, Juan
Montesinos, Victoriano
Nava, Elvis
Perez, Ethan
Lindner, David
contents 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, which is often very expensive. We study a more sample-efficient alternative: using pretrained vision-language models (VLMs) as zero-shot reward models (RMs) to specify tasks via natural language. We propose a natural and general approach to using VLMs as reward models, which we call VLM-RMs. We use VLM-RMs based on CLIP to train a MuJoCo humanoid to learn complex tasks without a manually specified reward function, such as kneeling, doing the splits, and sitting in a lotus position. For each of these tasks, we only provide a single sentence text prompt describing the desired task with minimal prompt engineering. We provide videos of the trained agents at: https://sites.google.com/view/vlm-rm. We can improve performance by providing a second "baseline" prompt and projecting out parts of the CLIP embedding space irrelevant to distinguish between goal and baseline. Further, we find a strong scaling effect for VLM-RMs: larger VLMs trained with more compute and data are better reward models. The failure modes of VLM-RMs we encountered are all related to known capability limitations of current VLMs, such as limited spatial reasoning ability or visually unrealistic environments that are far off-distribution for the VLM. We find that VLM-RMs are remarkably robust as long as the VLM is large enough. This suggests that future VLMs will become more and more useful reward models for a wide range of RL applications.
format Preprint
id arxiv_https___arxiv_org_abs_2310_12921
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
Rocamonde, Juan
Montesinos, Victoriano
Nava, Elvis
Perez, Ethan
Lindner, David
Machine Learning
Artificial Intelligence
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, which is often very expensive. We study a more sample-efficient alternative: using pretrained vision-language models (VLMs) as zero-shot reward models (RMs) to specify tasks via natural language. We propose a natural and general approach to using VLMs as reward models, which we call VLM-RMs. We use VLM-RMs based on CLIP to train a MuJoCo humanoid to learn complex tasks without a manually specified reward function, such as kneeling, doing the splits, and sitting in a lotus position. For each of these tasks, we only provide a single sentence text prompt describing the desired task with minimal prompt engineering. We provide videos of the trained agents at: https://sites.google.com/view/vlm-rm. We can improve performance by providing a second "baseline" prompt and projecting out parts of the CLIP embedding space irrelevant to distinguish between goal and baseline. Further, we find a strong scaling effect for VLM-RMs: larger VLMs trained with more compute and data are better reward models. The failure modes of VLM-RMs we encountered are all related to known capability limitations of current VLMs, such as limited spatial reasoning ability or visually unrealistic environments that are far off-distribution for the VLM. We find that VLM-RMs are remarkably robust as long as the VLM is large enough. This suggests that future VLMs will become more and more useful reward models for a wide range of RL applications.
title Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.12921