IEEE Lone Star Section Joint SMC/AESS Chapter Meeting
February 2020 meeting
Date and Time
Location
Hosts
Registration
- Date: 20 Feb 2020
- Time: 11:30 AM to 01:00 PM
- All times are (GMT-06:00) US/Central
- Add Event to Calendar
- 6220 Culebra Rd
- San Antonio, Texas
- United States 78238
- Building: SwRI Dining Services (Cafeteria)
- Room Number: Private Dining Room #2
- Click here for Map
- Contact Event Host
- Co-sponsored by Southwest Research Institute
- Starts 28 January 2020 05:32 PM
- Ends 19 February 2020 11:59 PM
- All times are (GMT-06:00) US/Central
- No Admission Charge
Speakers
Garrett Hall of Southwest Research Institute
Multi-Agent Reinforcement Learning in StarCraft II Environment
Reinforcement learning is a branch of machine learning which uses experiences to learn how to perform actions in an environment. The environment presented in this work is Star Craft II (SC2). SC2 is a real-time strategy game where two opponents use a variety of combat units and tactics to emerge victorious. Multiagent reinforcement learning algorithms learn unique behavioral policies for each of their agents.
This presentation’s main focus will be the “Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning” algorithm known as QMIX. Using QMIX’s combination of recurrent neural networks and hypernetworks, agents act in a cooperative manner during skirmishes in the SC2 environment. After a demonstration of QMIX is given at the various stages of training, the presenter will discuss his current joint Exploratory IR and Thesis progress and its relationship to QMIX.
Biography:
Mr. Hall has a B.S. degree in Electrical Engineering from the University of Texas at San Antonio (UTSA). Mr. Hall studied digital signal processing during his undergraduate degree. During this time, he worked in a brain computer interfacing laboratory collecting EEG signals which were classified using deep learning. The resulting signals were turned into commands for the flight of a Parrot AR Drone quadcopter. As a graduate student, he studied adversarial examples in the virtual environment of Unity. His algorithm took control of a ROS operated autonomous vehicle which was driven by a behavioral cloning neural network. It overrode the steering angle output based on the perturbation of the input image. Another project he worked on was sensor fusion for a HD web camera and a millimeter-wave radar using ROS. He is familiar with computer vision, digital image processing, object detection, and sematic segmentation. His current research focuses on simulations, artificial intelligence, supervised learning, reinforcement learning, and signal classification.
Mr. Hall is proficient in Python, Tensorflow, Keras, MATLAB, OpenCV and has experience in C, C++, and PyTorch.
Email:
Address:6220 Culebra Rd, , San Antonio, Texas, United States, 78238
Agenda
You are welcome to pick up your own lunch at the SwRI Dining Services lines and bring it to the Priviate Dining Room.