Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models

The proliferation of artificial intelligence is increasingly dependent on model understanding. Understanding demands both an interpretation - a human reasoning about a model's behavior - and an explanation - a symbolic representation of the functioning of the model. Notwithstanding the imperati...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-08
Main Authors: Maree, Charl, Omlin, Christian W
Format: Article
Language:English
Subjects:
Affinity
Agents (artificial intelligence)
Algorithms
Artificial intelligence
Investment strategy
Machine learning
Markov chains
Policies
Reasoning
Regularization
Representations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The proliferation of artificial intelligence is increasingly dependent on model understanding. Understanding demands both an interpretation - a human reasoning about a model's behavior - and an explanation - a symbolic representation of the functioning of the model. Notwithstanding the imperative of transparency for safety, trust, and acceptance, the opacity of state-of-the-art reinforcement learning algorithms conceals the rudiments of their learned strategies. We have developed a policy regularization method that asserts the global intrinsic affinities of learned strategies. These affinities provide a means of reasoning about a policy's behavior, thus making it inherently interpretable. We have demonstrated our method in personalized prosperity management where individuals' spending behavior in time dictate their investment strategies, i.e. distinct spending personalities may have dissimilar associations with different investment classes. We now explain our model by reproducing the underlying prototypical policies with discretized Markov models. These global surrogates are symbolic representations of the prototypical policies.
ISSN:2331-8422