You are here: Home Bernstein Seminar 2022 Joschka Boedecker: Inverse …

Banner Bernstein Seminar

Joschka Boedecker: Inverse Q-Learning as a Tool to Investigate Behavior and its Neural Correlates

Neurorobotics Lab | University of Freiburg [Bernstein Seminar]
When May 03, 2022
from 05:15 PM to 06:00 PM
Where Presence lecture, Bernstein Center, Lecture Hall (ground floor). Participation via Zoom: Meeting ID and password will be sent with e-mail invitation. You can also contact Fiona Siegfried for Meeting ID and password.
Contact Name
Add event to calendar vCal
iCal

Hybrid Format!

Abstract


Inverse Reinforcement Learning offers the promise to recover the intention underlying an observed behavior, i.e. a reward signal that would explain the behavior of an agent, assuming it tries to maximize it in the long term. This has important applications for imitation learning in robotics, as well as behavior understanding in fields such as biology and neuroscience. Most approaches that allow to extract such a signal from observed data, however, need to solve a full reinforcement learning problem to convergence multiple times in an inner loop, making them computationally expensive and unsuitable for many application scenarios.

In this talk, I will present our work on novel inverse RL algorithms which exploit the structure of Q-Learning and result in algorithms that speed up learning of the reward signal by several orders of magnitude, while also providing more accurate value estimates than prior work. I will also illustrate how this enables the analysis of behavior and the activity of brain regions of different animals as specific examples.

 

 About the speaker and his research

 Hosted by Christian Leibold

 

Supported by

Carl Zeiss FoundationNeurexNeurex | InterNeuronEU Development FundEU Interreg

 

All upcoming scientific events

Back to overview

All Bernstein Seminars

2024 |  202320222021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010

Filed under: