Combined Model for Partially-Observable and Non-Observable Task Switching: Solving Hierarchical Reinforcement Learning Problems Statically and Dynamically with Transfer Learning
Abstract
An integral function of fully autonomous robots and humans is the ability to focus attention on a few relevant percepts to reach a certain goal while disregarding irrelevant percepts. Humans and animals rely on the interactions between the Pre-Frontal Cortex (PFC) and the Basal Ganglia (BG) to achieve this focus called Working Memory (WM). The Working Memory Toolkit (WMtk) was developed based on a computational neuroscience model of this phenomenon with Temporal Difference (TD) Learning for autonomous systems. Recent adaptations of the toolkit either utilize Abstract Task Representations (ATRs) to solve Non-Observable (NO) tasks or storage of past input features to solve Partially-Observable (PO) tasks, but not both. We propose a new model, PONOWMtk, which combines both approaches, ATRs and input storage, with a static or dynamic number of ATRs. The results of our experiments show that PONOWMtk performs effectively for tasks that exhibit PO, NO, or both properties.
Cite
@article{arxiv.2004.06213,
title = {Combined Model for Partially-Observable and Non-Observable Task Switching: Solving Hierarchical Reinforcement Learning Problems Statically and Dynamically with Transfer Learning},
author = {Nibraas Khan and Joshua Phillips},
journal= {arXiv preprint arXiv:2004.06213},
year = {2020}
}
Comments
substantial text overlap with arXiv:1911.10425 which is the same as this paper. It was meant to be a revision of that paper, but I mistakenly submitted it as a new paper