Exploration in Knowledge Transfer Utilizing Reinforcement Learning
Preprint
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 $ε$-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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Exploration in deep reinforcement learning: A surveyInformation Fusion, 2022
- Target transfer Q-learning and its convergence analysisNeurocomputing, 2020
- Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes Using Transfer LearningIEEE Access, 2020
- Towards Knowledge Transfer in Deep Reinforcement Learning2016