Inverse Reinforcement Learning for Identifying Cognitive Radars
Virtual: https://events.vtools.ieee.org/m/318454This talk uses revealed preferences ideas stemming from microeconomics to develop inverse reinforcement learning methods in the context of cognitive radars. The talk comprises three parts. The first part develops inverse reinforcement learning algorithms to identify if a radar is cognitive, and to estimate the radar's utility function and constraints. The second part of the talk discusses how to design a radar that hides is cognition, i.e. how a cognitive radar can act dumb. Finally, we briefly discuss real time inverse reinforcement learning based on stochastic Lagenvin dynamics algorithms. Join Zoom Meeting https://udayton.zoom.us/j/82266160148?pwd=P5UedaxJ1xdV7_c-8sd4hFuOUvTGIT.1 Meeting ID: 822 6616 0148 Password: 878163 One tap mobile +13126266799,,82266160148# US (Chicago) +16465588656,,82266160148# US (New York) Dial by your location +1 312 626 6799 US (Chicago) +1 646 558 8656 US (New York) +1 301 715 8592 US (Washington DC) +1 346 248 7799 US (Houston) +1 669 900 9128 US (San Jose) +1 253 215 8782 US (Tacoma) Meeting ID: 822 6616 0148 Find your local number: https://udayton.zoom.us/u/kcv4yUzGYq Speaker(s): Dr. Vikram Krishnamurthy, Virtual: https://events.vtools.ieee.org/m/318454