BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

TL;DR

BlendRL is a neuro-symbolic reinforcement learning framework that combines neural and symbolic policies, leading to improved performance and robustness in Atari games compared to purely neural or symbolic approaches.

Contribution

This work introduces BlendRL, a novel framework that integrates symbolic reasoning with neural policies within reinforcement learning agents.

Findings

BlendRL outperforms neural and symbolic baselines in Atari environments.

BlendRL agents demonstrate robustness to environmental changes.

Analysis shows hybrid policies help overcome individual limitations.

Abstract

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that use mixtures of both logic and neural policies. We empirically demonstrate that BlendRL agents outperform both neural and symbolic baselines in standard Atari environments, and showcase their robustness to environmental changes. Additionally, we analyze the interaction between neural and symbolic policies, illustrating how their hybrid use helps agents overcome each other's limitations.