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

Hosung Lee, Sejin Kim, Seungpil Lee, Sanha Hwang, Jihwan Lee +2 more
7/30/2024
cs.AIcs.LG

No official code found. Best implementation: ConfeitoHS/arcle (73 stars, Apache-2.0, last commit 2024-08-30).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

ConfeitoHS/arcleCommunity100%
Apache-2.0

A Gymnasium-based Environment of the Abstraction and Reasoning Corpus (ARC)

739PythonAug 8, 20232 years agoApache-2.0
intelligence-testingprogram-synthesispsychometricsreinforcement-learning-environments

Similar Papers

Introduction to Reinforcement Learning

83% match1 repo22.2k2024

A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges

83% match2024

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

83% match1 repo122026

Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External Agents

83% match2025

Collaborating with language models for embodied reasoning

83% match2023

Reinforcement Learning is all You Need

83% match2025

Cite this paper

@article{lee2024arcle,
  title  = {ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning},
  author = {Hosung Lee and Sejin Kim and Seungpil Lee and Sanha Hwang and Jihwan Lee and Byung-Jun Lee and Sundong Kim},
  year   = {2024},
  eprint = {2407.20806},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.20806v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.20806.svg)](https://codeofpaper.com/paper/2407.20806)

Discussion