We study the problem of online adaptive policy selection for nonlinear time-varying discrete-time dynamical systems.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Since weak learners perform only marginallybetter than random guesses, such subroutines constitute aweakerassumption than the availability of an accurate supervised learning oracle. Weprovethat the sample complexity and running time bounds of the proposed method do not explicitly dependonthenumberofstates. While existing results on boosting operate on convex losses, the value function over policies is non-convex.

Drawing inspiration from recent advancements in model-based control, we introduce a novel class of policies centered on disturbance signals.

We study an algorithmic equivalence technique between non-convex gradient descent and convex mirror descent.

For this problem, with either a known or unknown system, we give an efficient sublinear regret algorithm.