Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples

TL;DR

This paper introduces Expert Q-learning, a deep reinforcement learning algorithm that integrates coarse state value assessments from offline experts to improve stability and performance, especially in non-deterministic environments.

Contribution

The paper presents a novel Expert Q-learning algorithm that incorporates offline expert assessments into deep Q-learning, enhancing robustness and reducing overestimation bias.

Findings

Expert Q-learning outperforms baseline Q-learning in Othello.

The new method shows increased stability in non-deterministic settings.

Expert Q-learning achieves higher scores than traditional algorithms.

Abstract

In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. We require that an offline expert assesses the value of a state in a coarse manner using three discrete values. An expert network is designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a combination of Double Q-learning and Dueling Q-learning. Our results show that Expert Q-learning is indeed useful and more resistant to the overestimation bias. The baseline Q-learning algorithm exhibits unstable and suboptimal behavior in non-deterministic settings, whereas Expert Q-learning demonstrates more robust performance with higher scores, illustrating that our algorithm is indeed suitable to integrate state values from expert examples into Q-learning.