Sebastien Gros

NTNU Trondheim

Monday, August 02, 2021, 14:00

virtual, see link below

One of the key motivations for using MPC in the context of Reinforcement Learning is the possibility to introduce formalism and guarantees in the context of RL. In particular, stability and safety guarantees can be discussed in the context of MPC-based RL. In this lecture, we will discuss recent results on that topic, and briefly present recent results extending the classic MPC stability tools to the framework of Markov Decision Processes. Finally, we will briefly go through a number of recent results on the combination of RL and MPC.

This talk is part of the summer school on model predictive control and reinforcement learning and openly available.

Join Zoom Meeting
https://uni-freiburg.zoom.us/j/65439158240?pwd=OHJrb2p2U2xDUEpVQTRBWWlvZGo0UT09

Meeting ID: 654 3915 8240
Passcode: 0uu1tq0ek