Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples
Peer reviewed, Journal article
Published version
Permanent lenke
https://hdl.handle.net/11250/3046765Utgivelsesdato
2022Metadata
Vis full innførselSamlinger
Originalversjon
Meng, L., Yazidi, A., Goodwin, M. & Engelstad, P. (2022). Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples. Proceedings of the Northern Lights Deep Learning Workshop, 3, 1-9. doi: 10.7557/18.6237Sammendrag
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 to incorporate 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.