Attend talk by @SahinLale tomorrow at 1pm PDT on learning + control at #ICML2020 workshop on Theoretical Foundations of #ReinforcementLearning We have exciting new results on achieving a logarithmic regret bound in partially observed adaptive control of LQG. @kazizzad @Caltechhttps://twitter.com/SahinLale/status/1283992063000801285 …
-
Show this thread
We use tools from control: predictive form of LQG to update estimates of system parameters in epochs and combine it with online learning to get optimal regret bounds. Poster session tomorrow at 1pm PDT: https://wensun.github.io/rl_theory_workshop_2020_ICML.github.io/ …
0 replies
1 retweet
6 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.