Constrained Learning for Dynamical Systems

Dia 2021-11-19 10:30:00-03:00
Hora 2021-11-19 10:30:00-03:00
Lugarzoom

Constrained Learning for Dynamical Systems

Santiago Paternain (Rensselaer Polytechnic Institute)

Learning has shown great success in recent years in controlling complex dynamical systems. However, for the most part, when training a policy most of the algorithms only consider a single objective function. However physical systems are required to satisfy a set of operation constraints, such as safety constraints or minimum performance levels. Naturally, one can express these problems as constrained optimization problems. These problems are in general non-convex and thus challenging. In this talk, I will establish that solving Reinforcement Learning problems under constraints is in fact not harder than solving unconstrained Reinforcement Learning problems.