ep5 - Sean Meyn: Markov chains, networks, reinforcement learning, beekeeping and jazz
inControl
00:00
RL: You've Been So Lucky, You Know?
RL: I've been so lucky. Just I don't know how I'm too lucky having these wonderful co-authors. My first sabbatical, he got a Fulbright scholarship, which funded my family, his two daughters,. His ex-wife, to go to Bangalore, India and the 90s. It was unbelievable. He says if a fluid model is stable, then this stochastic algorithm is stable. And that's a general principle for what's called stochastic approximation. The same thing holds with MCMC, Markov chain Monte Carlo.
Transcript
Play full episode
