ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Hosung, Kim, Sejin, Lee, Seungpil, Hwang, Sanha, Lee, Jihwan, Lee, Byung-Jun, Kim, Sundong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929442861875200
author Lee, Hosung
Kim, Sejin
Lee, Seungpil
Hwang, Sanha
Lee, Jihwan
Lee, Byung-Jun
Kim, Sundong
author_facet Lee, Hosung
Kim, Sejin
Lee, Seungpil
Hwang, Sanha
Lee, Jihwan
Lee, Byung-Jun
Kim, Sundong
contents This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based on these insights, we propose several research directions and motivations for using ARCLE, including MAML, GFlowNets, and World Models.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20806
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
Lee, Hosung
Kim, Sejin
Lee, Seungpil
Hwang, Sanha
Lee, Jihwan
Lee, Byung-Jun
Kim, Sundong
Artificial Intelligence
Machine Learning
This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based on these insights, we propose several research directions and motivations for using ARCLE, including MAML, GFlowNets, and World Models.
title ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2407.20806