Entropy-Guided Control Improvisation

TL;DR

The paper introduces ERCI, a framework for synthesizing control policies that balance hard, soft, and randomization constraints, supporting unpredictable behaviors in stochastic environments.

Contribution

It presents the ERCI framework and algorithm, enabling control policy synthesis with declarative constraints and quantifiable unpredictability, extending existing methods to handle combined adversarial and probabilistic uncertainties.

Findings

Supports arbitrary combinations of adversarial and probabilistic uncertainty

Remains computationally tractable for complex control synthesis

Enables control policies with specified unpredictability levels

Abstract

High level declarative constraints provide a powerful (and popular) way to define and construct control policies; however, most synthesis algorithms do not support specifying the degree of randomness (unpredictability) of the resulting controller. In many contexts, e.g., patrolling, testing, behavior prediction,and planning on idealized models, predictable or biased controllers are undesirable. To address these concerns, we introduce the \emph{Entropic Reactive Control Improvisation} (ERCI) framework and algorithm which supports synthesizing control policies for stochastic games that are declaratively specified by (i) a \emph{hard constraint} specifying what must occur, (ii) a \emph{soft constraint} specifying what typically occurs, and (iii) a \emph{randomization constraint} specifying the unpredictability and variety of the controller, as quantified using causal entropy. This framework, extends the state of the art by supporting arbitrary combinations of adversarial and probabilistic uncertainty in the environment. ERCI enables a flexible modeling formalism which we argue, theoretically and empirically, remains tractable.