ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
This work addresses the challenge of inductive reasoning for reinforcement learning researchers, but it is incremental as it builds on existing methods like PPO and focuses on a specific benchmark environment.
The paper tackles the problem of applying reinforcement learning to the Abstraction and Reasoning Corpus (ARC) by introducing ARCLE, an environment designed to address challenges like vast action spaces and hard-to-reach goals, and demonstrates that an agent using proximal policy optimization can learn individual tasks with performance enhancements from non-factorial policies and auxiliary losses.
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.