Author Date

2020-4

Degree Name

Department

Computer Science

College

Physical and Mathematical Sciences

Defense Date

2020-02-24

Publication Date

2020-03-11

First Faculty Advisor

David Wingate

First Faculty Reader

Jacob Crandall

Honors Coordinator

Seth Holladay

Keywords

reinforcement learning, machine learning, multi-task, multi-objective, transfer

Abstract

In the multi-objective reinforcement learning (MORL) paradigm, the relative importance of environment objectives is often unknown prior to training, so agents must learn to specialize their behavior to optimize different combinations of environment objectives that are specified post-training. These are typically linear combinations, so the agent is effectively parameterized by a weight vector that describes how to balance competing environment objectives. However, we show that behaviors can be successfully specified and learned by much more expressive non-linear logical specifications. We test our agent in several environments with various objectives and show that it can generalize to many never-before-seen specifications.