Physical Sciences and Mathematics Commons^™

Insights Into The Application Of Deep Reinforcement Learning In Healthcare And Materials Science, Benjamin R. Smith

Doctoral Dissertations

Reinforcement learning (RL) is a type of machine learning designed to optimize sequential decision-making. While controlled environments have served as a foundation for RL research, due to the growth in data volumes and deep learning methods, it is now increasingly being applied to real-world problems. In our work, we explore and attempt to overcome challenges that occur when applying RL to solve problems in healthcare and materials science.

First, we explore how issues in bias and data completeness affect healthcare applications of RL. To understand how bias has already been considered in this area, we survey the literature for existing …

The Basil Technique: Bias Adaptive Statistical Inference Learning Agents For Learning From Human Feedback, Jonathan Indigo Watson

Theses and Dissertations--Computer Science

We introduce a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown parameters. We present both the general framework for our technique and specific algorithms for biases drawn from a normal distribution. We evaluate our approach across various environments and tasks, comparing it to interactive and non-interactive machine learning methods, including deep learning techniques, using human trainers and a synthetic oracle with feedback distorted to varying degrees. …

Rocket Learn, Daanesh Ibrahim, Jules Stacy, David Stroud, Yusi Zhang

SMU Data Science Review

Abstract. This paper covers the development, testing, and implementation of Reinforcement Learning methods designed to autonomously learn and optimize Rocket League play. This study aims to analyze and benchmark model frameworks commonly used in Reinforcement Learning applications. These models can be applied to tasks ranging in difficulty from simple to superhumanly complex, and this study will begin with and build upon simple models performing simple tasks. It will result in complex models performing difficult tasks. Models will be allowed to train autonomously on the game using mass parallelization to expedite training times with the goal of maximizing reward function scores. …