Russia, 199178, St. Petersburg, 14 line V.O., 29B
+7 (812) 363-62-32
ru en

News

20.11.2020
“Data-Efficient Machine Learning for Autonomous Robots”

“Data-Efficient Machine Learning for Autonomous Robots”

Marc Deisenroth (University College London)

Colloquium of the Department of Mathematics and Computer Science

Thursday December 3 at 18:15 zoom ID 958-115-833

Abstract

 

In many high-impact areas of machine learning, we face the challenge of data-efficient learning, i.e., learning from scarce data. This includes healthcare, climate science, and autonomous robots. There are many approaches toward learning from scarce data. In this talk, I will discuss a few of them in the context of reinforcement learning. First, I will motivate probabilistic, model-based approaches to reinforcement learning, which allow us to reduce the effect of model errors. Second, I will discuss a meta-learning approach that allows us to generalize knowledge across tasks to enable few-shot learning.

Key references:

  • Marc P. Deisenroth, Dieter Fox, Carl E. Rasmussen, Gaussian Processes for Data-Efficient Learning in Robotics and Control, IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 37, pp. 408–423, 2015
  • Sanket Kamthe, Marc P. Deisenroth, Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control, Proceedings of the International the Conference on Artificial Intelligence and Statistics (AISTATS), 2018
  • Steindór Sæmundsson, Katja Hofmann, Marc P. Deisenroth, Meta Reinforcement Learning with Latent Variable Gaussian Processes, Proceedings of the International the Conference on Uncertainty in Artificial Intelligence, 2018

 

Everyone is welcome!