Bayesian Machine Learning for Controlling Autonomous Systems

Add to your list(s) Download to your calendar using vCal

• Marc Deisenroth, Imperial College
• Tuesday 17 December 2013, 14:00-15:00
• Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB.

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

This talk has been canceled/deleted

Autonomous learning has been a promising direction in control and robotics for more than a decade since learning models and controllers from data allows us to reduce the amount of engineering knowledge that is otherwise required. Due to their flexibility, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers. However, in real systems, such as robots, many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, pre-shaped policies, or specific knowledge about the underlying dynamics.

In the first part of the talk, we follow a different approach and speed up learning by efficiently extracting information from sparse data. In particular, we learn a probabilistic, non-parametric Gaussian process dynamics model. By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of model errors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves an unprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks.

In the second part of my talk, we will discuss an alternative method for learning controllers based on Bayesian Optimization, where it is no longer possible to learn models of the underlying dynamics. We successfully applied Bayesian optimization to learning controller parameters for a bipedal robot, where modelling the dynamics is very difficult due to ground contacts. Using Bayesian optimization, we sidestep this modelling issue and directly optimize the controller parameters without the need of modelling the robot’s dynamics.

This talk is part of the Microsoft Research Cambridge, public talks series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.