Controllable Information Production
This work addresses the challenge of designing intrinsic motivation methods without designer-specified variables, which is incremental in the field of AI and robotics.
The authors tackled the problem of generating intelligent behavior without external utilities by introducing Controllable Information Production (CIP), a novel intrinsic motivation principle derived from Optimal Control, and demonstrated its effectiveness on standard benchmarks.
Intrinsic Motivation (IM) is a paradigm for generating intelligent behavior without external utilities. The existing information-theoretic methods for IM are predominantly based on information transmission, which explicitly depends on the designer's choice of which random variables engage in transmission. In this work, we introduce a novel IM principle, Controllable Information Production (CIP), that avoids both external utilities and designer-specified variables. We derive the CIP objective from Optimal Control, showing a connection between extrinsic and intrinsic behaviors. CIP appears as the gap between open-loop and closed-loop Kolmogorov-Sinai entropies, which simultaneously rewards the pursuit and regulation of chaos. We establish key theoretical properties of CIP and demonstrate its effectiveness on standard IM benchmarks.