Dr. Pratap Tokekar Research Group – Computer Science, University of Maryland

Dr. Alec Koppel Johns Hopkins University Applied Physics Laboratory

You are invited to the February talk in a speaker series presented by the Johns Hopkins Institute for Assured Autonomy (IAA), featuring national scholars presenting new research and development at the intersection of autonomy and assurance. These talks will be presented virtually on Monday, February 9, at 1 p.m. This event is open to all APL and JHU staff, faculty, and students; please share!

This seminar will consist of two talks:

1. A Perspective on Safety, Risk, and Reproducibility in Reinforcement Learning, presented by Alec Koppel, Senior Professional Staff member (Senior Scientist) at the Johns Hopkins University Applied Physics Laboratory within the Artificial Intelligence/Machine Learning Group in the Research and Exploratory Development Department.
ABSTRACT:
Reinforcement learning is a field that has gained salience in recent years, dating back to the 1990s with Backgammon playing bots, and more recently, with AlphaGo and training mechanisms for large language models. Reinforcement learning may refer to a problem, a learning paradigm, a collection of techniques, and so on, but irrespective of its designation, it is rife with disparate sources of randomness. We provide some perspective on how communities, spanning operations research, computer science, electrical engineering, and statistics, have tried to quantify and mitigate them. These mitigation strategies include safety, learning with constraints, risk measures, reproducibility, simulator calibration, and data coverage concerns. Time permitting, we’ll cover some emerging techniques to enforce reproducibility constraints into the standard RL training pipeline.

2. Reliable Reinforcement Learning for Robot Autonomy, presented by Pratap Tokekar, Associate Professor in the Department of Computer Science at the University of Maryland and Amazon Scholar at Amazon Robotics.
ABSTRACT:
The speaker will review recent trends in safe and reliable reinforcement learning for the control of robotic autonomous systems. The Robotics Algorithms & Autonomous Systems (RAAS) Lab designs algorithms and build systems to enable teams of robots to act as sensing agents, with research at the intersection of theory and systems and which is motivated by real-world applications to environmental monitoring, infrastructure inspection, and precision agriculture.

Connection Information:

JHU/IAA Seminar: Talk Trends in Safe and Reliable Reinforcement Learning
Meeting Time:
Feb 9, 2026 01:00 PM Eastern Time (US and Canada)
To join the meeting, please click below:
https://jhuapl.zoomgov.com/j/1602870267?pwd=aqWGgbyuvpbxoDYNeoL0OSb0TyGY0t.1
Phone one-tap
US: +16692545252,,1602870267# or +16469641167,,1602870267#
Meeting ID: 160 287 0267
Password: 324738