Learning to Assist Humans without Inferring Rewards

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Myers, Vivek, Ellis, Evan, Levine, Sergey, Eysenbach, Benjamin, Dragan, Anca
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916567824990208
author Myers, Vivek
Ellis, Evan
Levine, Sergey
Eysenbach, Benjamin
Dragan, Anca
author_facet Myers, Vivek
Ellis, Evan
Levine, Sergey
Eysenbach, Benjamin
Dragan, Anca
contents Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects actions to help the human reach that goal. This approach requires inferring intentions, which can be difficult in high-dimensional settings. We build upon prior work that studies assistance through the lens of empowerment: an assistive agent aims to maximize the influence of the human's actions such that they exert a greater control over the environmental outcomes and can solve tasks in fewer steps. We lift the major limitation of prior work in this area--scalability to high-dimensional settings--with contrastive successor representations. We formally prove that these representations estimate a similar notion of empowerment to that studied by prior work and provide a ready-made mechanism for optimizing it. Empirically, our proposed method outperforms prior methods on synthetic benchmarks, and scales to Overcooked, a cooperative game setting. Theoretically, our work connects ideas from information theory, neuroscience, and reinforcement learning, and charts a path for representations to play a critical role in solving assistive problems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02623
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Assist Humans without Inferring Rewards
Myers, Vivek
Ellis, Evan
Levine, Sergey
Eysenbach, Benjamin
Dragan, Anca
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Machine Learning
Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects actions to help the human reach that goal. This approach requires inferring intentions, which can be difficult in high-dimensional settings. We build upon prior work that studies assistance through the lens of empowerment: an assistive agent aims to maximize the influence of the human's actions such that they exert a greater control over the environmental outcomes and can solve tasks in fewer steps. We lift the major limitation of prior work in this area--scalability to high-dimensional settings--with contrastive successor representations. We formally prove that these representations estimate a similar notion of empowerment to that studied by prior work and provide a ready-made mechanism for optimizing it. Empirically, our proposed method outperforms prior methods on synthetic benchmarks, and scales to Overcooked, a cooperative game setting. Theoretically, our work connects ideas from information theory, neuroscience, and reinforcement learning, and charts a path for representations to play a critical role in solving assistive problems.
title Learning to Assist Humans without Inferring Rewards
topic Artificial Intelligence
Computers and Society
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2411.02623