Human-Allied Relational Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Darvishvand, Fateme Golivand, Shindo, Hikaru, Sidheekh, Sahil, Kersting, Kristian, Natarajan, Sriraam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908600572575744
author Darvishvand, Fateme Golivand
Shindo, Hikaru
Sidheekh, Sahil
Kersting, Kristian
Natarajan, Sriraam
author_facet Darvishvand, Fateme Golivand
Shindo, Hikaru
Sidheekh, Sahil
Kersting, Kristian
Natarajan, Sriraam
contents Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists in the problem. Consequently, relational extensions (RRL) have been developed for such structured problems that allow for effective generalization to arbitrary number of objects. However, they inherently make strong assumptions about the problem structure. We introduce a novel framework that combines RRL with object-centric representation to handle both structured and unstructured data. We enhance learning by allowing the system to actively query the human expert for guidance by explicitly modeling the uncertainty over the policy. Our empirical evaluation demonstrates the effectiveness and efficiency of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16188
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-Allied Relational Reinforcement Learning
Darvishvand, Fateme Golivand
Shindo, Hikaru
Sidheekh, Sahil
Kersting, Kristian
Natarajan, Sriraam
Machine Learning
Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists in the problem. Consequently, relational extensions (RRL) have been developed for such structured problems that allow for effective generalization to arbitrary number of objects. However, they inherently make strong assumptions about the problem structure. We introduce a novel framework that combines RRL with object-centric representation to handle both structured and unstructured data. We enhance learning by allowing the system to actively query the human expert for guidance by explicitly modeling the uncertainty over the policy. Our empirical evaluation demonstrates the effectiveness and efficiency of our proposed approach.
title Human-Allied Relational Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2510.16188