A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines

TL;DR

This paper introduces Extreme Q-Learning Machine (EQLM), a new reinforcement learning update method based on Extreme Learning Machines, demonstrating comparable performance to traditional Q-Networks on the cart-pole benchmark.

Contribution

The paper proposes a novel update mechanism for Q-learning using Extreme Learning Machines, expanding the methods available beyond gradient-based neural network training.

Findings

EQLM achieves similar long-term performance to Q-Networks on cart-pole.

EQLM offers a potentially faster training alternative to gradient-based updates.

The approach broadens the exploration of update mechanisms in reinforcement learning.

Abstract

Reinforcement learning is a popular machine learning paradigm which can find near optimal solutions to complex problems. Most often, these procedures involve function approximation using neural networks with gradient based updates to optimise weights for the problem being considered. While this common approach generally works well, there are other update mechanisms which are largely unexplored in reinforcement learning. One such mechanism is Extreme Learning Machines. These were initially proposed to drastically improve the training speed of neural networks and have since seen many applications. Here we attempt to apply extreme learning machines to a reinforcement learning problem in the same manner as gradient based updates. This new algorithm is called Extreme Q-Learning Machine (EQLM). We compare its performance to a typical Q-Network on the cart-pole task - a benchmark reinforcement learning problem - and show EQLM has similar long-term learning performance to a Q-Network.