Adaptive Multi-stage Sampling for Risk Sensitive Control
Abstract: Most applications of stochastic control involve optimization over expected or mean outcomes. Unfortunately, this does not account for a decision maker’s desire to reduce variability or the occurrence of rare, disastrous events. Risk sensitive control introduces dynamic, time-consistent risk measures to create policies that minimize risk in sequential decision making under uncertainty. In this talk we discuss an adaptive sampling based algorithm for risk sensitive control, aimed at mitigating the computational cost involved. We present the results of simulations of risk sensitive benchmarks to demonstrate the feasibility of this approach.
Date and Time
Location
Hosts
Registration
- Date: 28 Jun 2023
- Time: 06:30 PM to 08:00 PM
- All times are (UTC-04:00) Eastern Time (US & Canada)
-
Add Event to Calendar
- George Mason University
- 4511 Patriot Circle
- Fairfax, Virginia
- United States 22030
- Building: Nguyen Engineering
- Room Number: Ground Floor - Jajodia Auditorium
- Click here for Map
- Starts 21 June 2023 12:00 AM
- Ends 29 June 2023 12:00 AM
- All times are (UTC-04:00) Eastern Time (US & Canada)
- No Admission Charge
Speakers
Brian Rybicki of US Naval Research Laboratory
Optimal Control
Biography:
Brian Rybicki is a PhD candidate in Electrical and Computer Engineering at George Mason University and a full-time Electronics Engineer at the Naval Research Laboratory (NRL). He received a B.S. and M.S. in Electrical Engineering from the Pennsylvania State University in 2006 and 2008. From 2008 to 2012, he was an associate staff member at MIT Lincoln Laboratory. He has been with NRL since 2012. His research interests include reinforcement learning, optimal control, and game-theoretic methods for defense applications.
Agenda
6:30pm-7:00pm: Light dinner and refreshments
7:00pm-8:00pm: Talk with Q&A