Date of Award

Spring 2019

Degree Type

Masters Thesis

Degree Name

Master of Science (MS)

School

Computing Sciences and Computer Engineering

Committee Chair

Bikramjit Banerjee

Committee Chair School

Computing Sciences and Computer Engineering

Committee Member 2

Dia Ali

Committee Member 2 School

Computing Sciences and Computer Engineering

Committee Member 3

Beddhu Murali

Committee Member 3 School

Computing Sciences and Computer Engineering

Abstract

Learning from human demonstration (LfD), among many speedup techniques for reinforcement learning (RL), has seen many successful applications. We consider one LfD technique called Human Agent Transfer (HAT), where a model of the human demonstrator’s decision function is induced via supervised learning, and used as an initial bias for RL. Some recent work in LfD have investigated learning from observations only, i.e., when only the demonstrator’s states (and not its actions) are available to the learner. Since the demonstrator’s actions are treated as labels for HAT, supervised learning becomes untenable in their absence. We adapt the idea of learning an inverse dynamics model from the data acquired by the learner’s interactions with the environment, and deploy it to fill in the missing actions of the demonstrator. The resulting version of HAT—called State-only HAT (SoHAT)—is experimentally shown to preserve some advantages of HAT in benchmark domains with both discrete and continuous actions. This thesis also establishes principled modifications of an existing baseline algorithm—called A3C—to create its HAT and SoHAT variants that are used in our experiments.

Available for download on Wednesday, May 09, 2029

Share

COinS