File(s) under permanent embargo

Memory-based explainable reinforcement learning

conference contribution
posted on 01.01.2019, 00:00 authored by F Cruz Naranjo, Richard DazeleyRichard Dazeley, P Vamplew
Reinforcement learning (RL) is a learning approach based on behavioral psychology used by artificial agents to learn autonomously by interacting with their environment. An open issue in RL is the lack of visibility and understanding for end-users in terms of decisions taken by an agent during the learning process. One way to overcome this issue is to endow the agent with the ability to explain in simple terms why a particular action is taken in a particular situation. In this work, we propose a memory-based explainable reinforcement learning (MXRL) approach. Using an episodic memory, the RL agent is able to explain its decisions by using the probability of success and the number of transactions to reach the goal state. We have performed experiments considering two variations of a simulated scenario, namely, an unbounded grid world with aversive regions and a bounded grid world. The obtained results show that the agent, using information extracted from the memory, is able to explain its behavior in an understandable manner for non-expert end-users at any moment during its operation.

History

Event

Artificial Intelligence. Conference (32nd : 2019 : Adelaide, S. Aust.)

Volume

11919

Series

Artificial Intelligence Conference

Pagination

66 - 77

Publisher

Springer

Location

Adelaide, S. Aust.

Place of publication

Cham, Switzerland

Start date

02/12/2019

End date

05/12/2019

ISSN

0302-9743

eISSN

1611-3349

ISBN-13

9783030352875

Language

eng

Publication classification

E1 Full written paper - refereed

Editor/Contributor(s)

J Liu, J Bailey

Title of proceedings

AI 2019: Advances in artificial intelligence : Proceedings of the 32nd Australasian Joint Conference on Artificial Intelligence 2019