Efficient Variational Sequential Information Control
Keywords: POMDP, Mutual Information, Variational methods, Intrinsically motivated, ADF, EP
Abstract: We develop a family of fast variational methods for sequential control in dynamical settings where an agent is incentivized to maximize information gain. We consider the case of optimal control in continuous nonlinear dynamical systems that prohibit exact evaluation of the mutual information (MI) reward. Our approach couples efficient message-passing inference with variational bounds on the MI objective under Gaussian projections. We also develop a Gaussian mixture approximation that enables exact MI evaluation under constraints on the component covariances. We validate our methodology in nonlinear systems with superior and faster control compared to standard particle-based methods. We show our approach improves the accuracy and efficiency of one-shot robotic learning with intrinsic MI rewards.
Submission Number: 48
Loading