BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shindo, Hikaru, Delfosse, Quentin, Dhami, Devendra Singh, Kersting, Kristian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915250757959680
author Shindo, Hikaru
Delfosse, Quentin
Dhami, Devendra Singh
Kersting, Kristian
author_facet Shindo, Hikaru
Delfosse, Quentin
Dhami, Devendra Singh
Kersting, Kristian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
Shindo, Hikaru
Delfosse, Quentin
Dhami, Devendra Singh
Kersting, Kristian
Machine Learning
Artificial Intelligence
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.
title BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.11689