Safe Reinforcement Learning (SRL) Using Control Barrier Functions

Safe Reinforcement Learning (SRL) Using Control Barrier Functions

Abstract:

This talk presents a method to learn barrier-certified safe controllers for safety-critical systems while providing an optimal performance with the focus on reinforcement learning approach. The problem describes designing optimal controllers for systems with unknown dynamics through the interaction while safety specifications of the system such as state constraints must be satisfied. We first start by reviewing the basics of reinforcement learning in control such as the overall framework, Bellman equation, actor/critic approximations and sequential improvement of controller by means of reducing the prediction error. Then, different types of control barrier functions and their application for restricting the states of the system within a desired safe region and therefore safety guarantee are discussed. The safe reinforcement learning problem is then formulated by means of control barrier functions to have a safe performance. Safety, stability and optimality of the proposed method are discussed and finally the off-policy reinforcement learning algorithm to implement the proposed method is presented.

Webinar Teaser

Date: Monday, May 31, 2021 (9 Khordad 1400)

Time: 18:00-19:30 (+4:30 GMT Tehran local time) 9:30-11:30 (-4:00 GMT Canada Eastern Time Zone)

, ,
Previous Post
Safeguarding Public Health During Infectious Disease Pandemics Using Medical Robotics, Wearable Technology, and AI Workshop
Next Post
ARAS-Farabi Agreement for Further Collaboration

Related Posts

Leave a Reply

Your email address will not be published.

Fill out this field
Fill out this field
Please enter a valid email address.
You need to agree with the terms to proceed

Menu