Decision & Control Spring Lecture Series || Approximate information states for partially observable systems

Event Type
Seminar/Symposium
Sponsor
Decision & Control
Location
Virtual
Date
February 8, 2023 3:00 PM - 4:00 PM
Speaker
Aditya Mahajan || Associate Professor of Electrical and Computer Engineering at McGill University
Cost
Registration
Contact
Stephanie
Email
smccu4@illinois.edu
Phone
217-244-1033

Zoom meeting info:

Topic: DCL Seminar Aditya Mahajan

Time: Feb 8, 2023 03:00 PM Central Time (US and Canada)

 

Join Zoom Meeting

https://illinois.zoom.us/j/82630911556?pwd=SlhEWFVRUXEvUFc5Zmp2VkhIUE93Zz09

 

Meeting ID: 826 3091 1556

Password: 967113

 

 

Speaker: Aditya Mahajan


 Title: Approximate information states for partially observable systems
 
 Abstract: Reinforcement learning (RL) provides a conceptual framework for designing agents which learn to act optimally in unknown environments. RL has been successfully used in various applications ranging from robotics, industrial automation, finance, healthcare, and natural language processing. The success of RL is based on a solid foundation of combining the theory of exact and approximate Markov decision processes (MDPs) with iterative algorithms that are guaranteed to learn an exact or approximate action-value function and/or an approximately optimal policy. However, for the most part, the research on RL theory is focused on systems with full state observations.
 
 In various applications including robotics, finance, and healthcare, the agent only gets a partial observation of the state of the environment. In this talk, I will describe a new framework for approximate planning and learning for partially observed systems based on the notion of approximate information state. The talk will highlight the strong theoretical foundations of this framework, illustrate how many of the existing approximation results can be viewed as a special case of approximate information state, and provide empirical evidence which suggests that this approach works well in practice.
 
 Joint work with Jayakumar Subramanian, Amit Sinha, Raihan Seraj, and Erfan Seyedsalehi
 
 Bio: Aditya Mahajan is an Associate Professor of Electrical and Computer Engineering at McGill University, Montreal, Canada. He is affiliated with the McGill Center of Intelligent Machines (CIM), Montreal Institute of Learning Algorithms (Mila), and Group for research in decision analysis (GERAD). He received the B.Tech degree in Electrical Engineering from the Indian Institute of Technology, Kanpur, India in 2003 and the MS and PhD degrees in Electrical Engineering and Computer Science from the University of Michigan, Ann Arbor, USA in 2006 and 2008. His principal research interests are learning and control of decentralized stochastic system.