[] Speaker(s): Chitra Agenda: 4:00- Meet and Greet 4:10- Introduction by Ratna Raj WECE Advisor 4:15- Presentation by guest speaker: Chitra Venkatraman 5:00-5:30 Networking Room: 115, Bldg: ECEC, 323 Martin Luther King Drive, Newark, New Jersey, United States, 07039
The IEEE North Jersey Section's Executive Committee (EXCOM) monthly meeting will be held hybridly. The EXCOM meeting starts at 6:30 pm EST and typically ends at 8:30 pm. The meeting is meant to discuss and coordinate the activities of the Section and its Chapters and Groups, as well as new initiatives. Everyone is welcome to attend this meeting. Please register in advance for this meeting using vTools (Please make a note if you join the meeting remotely) You can change/cancel the registration if your plans change. For more information, please contact our IEEE North Jersey Section Chair Hong Zhao ([email protected]) , or Secretary, Adriaan van Wijngaarden, ([email protected]). Location: New Jersey Institute of Technology To join remotely by the following Zoom link: https://fdu.zoom.us/j/99736508515 Meeting ID: 997 3650 8515 Note: If you are unable to join the meeting, please send your chapter activity report to the section chair at [email protected] Agenda: 06:30 pm - 06:45 pm Networking 06:45 pm - 08:30 pm IEEE North Jersey Section Executive Committee Meeting The meeting agenda typically includes news related to the IEEE and the IEEE North Jersey Section, Secretary and Treasurer reports, Chapter and Affinity Group reports, Committee reports, and reports by various Chairs and Representatives, Committee Chairs, and planning, and new initiatives. Room: ECE 202, Bldg: Electrical and Computer Engineering (ECE) Building, University Heights, Newark, New Jersey, United States, 07102, Virtual: https://events.vtools.ieee.org/m/441739
Abstract: Many constrained sequential decision-making processes, such as safe AV navigation, wireless network control, caching, cloud computing, etc., can be cast as Constrained Markov Decision Processes (CMDP). Reinforcement Learning (RL) algorithms have been used to learn optimal policies for unknown unconstrained MDP. Extending these RL algorithms to unknown CMDP brings the additional challenge of maximizing the reward and satisfying the constraints. In this talk, I will present algorithms that can learn safe policies effectively. In the second part of the talk, I will demonstrate how the theoretical understanding of the constrained MDP can help us to develop algorithms for practical applications. As an application, I show how to learn to obtain optimal beam directions under time-varying interference-constrained channels for a mobile service robot. Optimal beam selection in mmWave is challenging because of its time-varying nature. We propose a primal-dual Gaussian process bandit with adaptive reinitialization to handle non-stationarity and interference constraints. We demonstrate how our approach learns to adapt effectively to time-varying channel conditions. Co-sponsored by: IEEE North Jersey Section Speaker(s): Dr. Arnob Ghosh, Agenda: Nov 6th, Talk: 7:00 PM - 8:00 PM Discussion Q/A: 8:00 PM - 8:15 PM Room: ECE 202, Bldg: Electrical and Computer Engineering, 154 Summit Street, Newark, New Jersey, United States, 07102
