Reinforcement Learning Your Way: Agent Characterization through Policy Regularization

4Citations
Citations of this article
13Readers
Mendeley users who have this article in their library.

Abstract

The increased complexity of state-of-the-art reinforcement learning (RL) algorithms has resulted in an opacity that inhibits explainability and understanding. This has led to the development of several post hoc explainability methods that aim to extract information from learned policies, thus aiding explainability. These methods rely on empirical observations of the policy, and thus aim to generalize a characterization of agents’ behaviour. In this study, we have instead developed a method to imbue agents’ policies with a characteristic behaviour through regularization of their objective functions. Our method guides the agents’ behaviour during learning, which results in an intrinsic characterization; it connects the learning process with model explanation. We provide a formal argument and empirical evidence for the viability of our method. In future work, we intend to employ it to develop agents that optimize individual financial customers’ investment portfolios based on their spending personalities.

References Powered by Scopus

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

5442Citations
N/AReaders
Get full text

Markov games as a framework for multi-agent reinforcement learning

2153Citations
N/AReaders
Get full text

Explainability in deep reinforcement learning

249Citations
N/AReaders
Get full text

Cited by Powered by Scopus

A Non-Invasive Method Based on AI and Current Measurements for the Detection of Faults in Three-Phase Motors

8Citations
N/AReaders
Get full text

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

3Citations
N/AReaders
Get full text

Localized Affinity-Based Reinforcement Learning for Interpretable State-Specific Decision-Making

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Maree, C., & Omlin, C. (2022). Reinforcement Learning Your Way: Agent Characterization through Policy Regularization. AI (Switzerland), 3(2), 250–259. https://doi.org/10.3390/ai3020015

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 3

60%

Lecturer / Post doc 1

20%

Researcher 1

20%

Readers' Discipline

Tooltip

Philosophy 2

33%

Engineering 2

33%

Computer Science 1

17%

Environmental Science 1

17%

Article Metrics

Tooltip
Mentions
Blog Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free