LIVE Talk | Robots Learning in Simulation | 18:30 (UK time), 16 February 2021.

LIVE streaming at YouTube

18:30 (UK time), 16 February 2021.

Summary:

‘The development of autonomous robots would be a significant accomplishment for society. Autonomous robots require the ability to learn from interaction: to try new actions, observe success and failure, and tie effects back to causes. In this talk I will describe how we can create robots that learn through interaction. Instead of being programmed to complete a task, such learning robots can figure out the right way to accomplish the task on their own. I’ll further discuss how my own research aims to develop robots that can learn in simulations of the real world to speed up how long it takes robots to acquire new skills.’

The Speaker

Josiah Hanna is a post-doc in the School of Informatics at the University of Edinburgh working with Stefano Albrecht. Starting August 2021, he will be an assistant professor in the Department of Computer Sciences at the University of Wisconsin — Madison. He received his Ph.D. in the Computer Science Department at the University of Texas at Austin advised by Peter Stone. Prior to attending UT Austin, he completed his B.S. in computer science and mathematics at the University of Kentucky advised by Judy Goldsmith. Josiah is a recipient of the NSF Graduate Research Fellowship and the IBM Ph.D. Fellowship.

His research interests lie in artificial intelligence and machine learning, seeking to develop algorithms that allow AI agents to learn (quickly) from experience. In particular, he studies reinforcement learning which is an area of AI research that models and develops algorithms for learning through interaction. Josiah’s research seeks to increase the practical applicability of reinforcement learning to real world problems such as robotics.

Want to find out more?

For more information, visit the links below:

A great textbook on reinforcement learning: //incompleteideas.net/book/the-book.html

Wikipedia page: https://en.wikipedia.org/wiki/Reinforcement_learning

Getting started in RL research: https://spinningup.openai.com/en/latest/index.html

What We Need From You

To facilitate the Q&A session, please leave your questions in the comment section below. Our host will collate them in advance for the speaker to answer during the talk. You are of course very welcome to ask questions live as well.
Here is the link to our YouTube channel for you to access the talk: https://www.youtube.com/channel/UCNLjdnS8qSZfJ2nBFBfdP4g
Hope to see you there!