Archived record · Edyssy 2014

CPS: Breakthrough: Reinforcement Learning Algorithms for Cyber-Physical Systems

Agency

NSFNational Science Foundation

Principal investigator

Peter Stone

Institution

University of Texas at Austin

Amount listed

$499,760

Period

Oct. 1, 2013 to Sept. 30, 2016

Abstract

This project investigates new reinforcement learning algorithms to enable long-term real-time autonomous learning by cyber-physical systems (CPS). The complexity of CPS makes hand-programming safe and efficient controllers for them difficult. For CPS to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes with potential for solving this problem. However, existing RL algorithms do not meet all of the requirements of learning in CPS. Efficacy of the new algorithms for CPS is evaluated in the context of smart buildings and autonomous vehicles.<br/><br/>Cyber-physical systems (CPS) have the potential to revolutionize society by enabling smart buildings, transportation, medical technology, and electric grids. Success of this project could lead to a new generation of CPS that are capable of adapting to their situation and improving their performance autonomously over time. In addition to the traditional methods of dissemination, this project will develop and release open-source code implementing the new reinforcement learning algorithms. Education and outreach activities associated with the project include a Freshman Research Initiative course, participation in a UT Austin annual open house that draws in many underrepresented minorities to interest the public in computer science and science in general, and the department's annual summer school for high school girls called First Bytes.

Reading this record as an applicant

The record names Peter Stone at University of Texas at Austin as principal investigator. When a professor holds an award like this, part of the budget usually goes to people: graduate research assistants, a postdoc or a technician. A 3-year award leaves room for a student to join partway through. Look up the investigator’s current awards before you write; a 2014 record is a lead, not a promise. Before you do, read up on getting a letter from a well-known investigator.

Start with the investigator’s faculty page and recent papers, then search their name in NIH RePORTER or NSF Award Search to see what is active now. The grant search guide walks through it.