Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task

TL;DR

This paper introduces SOLAR, a new dataset and generator to enable offline RL for complex decision-making in ARC, demonstrating improved reasoning in a simple task.

Contribution

We created SOLAR and the SOLAR-Generator to provide sufficient data for offline RL in ARC, and validated their effectiveness with LDCQ on a simple task.

Findings

Offline RL with SOLAR improves decision-making in ARC

LDCQ successfully identifies correct answer states

Generated data enables strategic reasoning in complex environments

Abstract

Effective long-term strategies enable AI systems to navigate complex environments by making sequential decisions over extended horizons. Similarly, reinforcement learning (RL) agents optimize decisions across sequences to maximize rewards, even without immediate feedback. To verify that Latent Diffusion-Constrained Q-learning (LDCQ), a prominent diffusion-based offline RL method, demonstrates strong reasoning abilities in multi-step decision-making, we aimed to evaluate its performance on the Abstraction and Reasoning Corpus (ARC). However, applying offline RL methodologies to enhance strategic reasoning in AI for solving tasks in ARC is challenging due to the lack of sufficient experience data in the ARC training set. To address this limitation, we introduce an augmented offline RL dataset for ARC, called Synthesized Offline Learning Data for Abstraction and Reasoning (SOLAR), along with the SOLAR-Generator, which generates diverse trajectory data based on predefined rules. SOLAR enables the application of offline RL methods by offering sufficient experience data. We synthesized SOLAR for a simple task and used it to train an agent with the LDCQ method. Our experiments demonstrate the effectiveness of the offline RL approach on a simple ARC task, showing the agent's ability to make multi-step sequential decisions and correctly identify answer states. These results highlight the potential of the offline RL approach to enhance AI's strategic reasoning capabilities.