Exploration in Knowledge Transfer Utilizing Reinforcement Learning

TL;DR

This paper compares exploration strategies in deep transfer learning for reinforcement learning, finding that the upper confidence bound method outperforms others in a virtual drone task.

Contribution

It evaluates and compares multiple exploration methods within a deep transfer learning framework, highlighting the superior performance of the upper confidence bound approach.

Findings

UCB exploration outperforms epsilon-greedy and Boltzmann methods.

The study demonstrates the effectiveness of exploration strategies in transfer learning.

Results are based on a virtual drone problem simulation.

Abstract

The contribution focuses on the problem of exploration within the task of knowledge transfer. Knowledge transfer refers to the useful application of the knowledge gained while learning the source task in the target task. The intended benefit of knowledge transfer is to speed up the learning process of the target task. The article aims to compare several exploration methods used within a deep transfer learning algorithm, particularly Deep Target Transfer $Q$-learning. The methods used are $\epsilon$-greedy, Boltzmann, and upper confidence bound exploration. The aforementioned transfer learning algorithms and exploration methods were tested on the virtual drone problem. The results have shown that the upper confidence bound algorithm performs the best out of these options. Its sustainability to other applications is to be checked.