Information Theoretic Regret Bounds for Online Nonlinear Control

Abstract

This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space. This framework yields a general setting that permits discrete and continuous control inputs as well as non-smooth, non-differentiable dynamics. Our main result, the Lower Confidence-based Continuous Control ($L{C}^3$) algorithm, enjoys a near-optimal $O(\sqrt{T})$ regret bound against the optimal controller in episodic settings, where $T$ is the number of episodes. The bound has no explicit dependence on dimension of the system dynamics, which could be infinite, but instead only depends on information theoretic quantities. We empirically show its application to a number of nonlinear control tasks and demonstrate the benefit of exploration for learning model dynamics.

References in corpus (9)

• Solving Rubik's Cube with a Robot Hand
• Benchmarking Model-Based Reinforcement Learning
• Contextual Decision Processes with Low Bellman Rank are PAC-Learnable
• Exploring Model-based Planning with Policy Networks
• Model-Based Reinforcement Learning with Value-Targeted Regression
• Active Learning for Nonlinear System Identification with Guarantees
• Information-Theoretic Confidence Bounds for Reinforcement Learning
• The Nonstochastic Control Problem
• Lyceum: An efficient and scalable ecosystem for robot learning