Long-term planning, as in reinforcement learning (RL), involves finding strategies: actions that collectively work toward a goal rather than individually optimizing their immediate outcomes. As part of a strategy, some actions are taken at the expense of short-term benefit to enable future actions with even greater returns. These actions are only advantageous if followed up by the actions they facilitate, consequently, they would not have been taken if those follow-ups were not available. In this paper, we quantify such dependencies between planned actions with strategic link scores: the drop in the likelihood of one decision under the constraint that a follow-up decision is no longer available. We demonstrate the utility of strategic link scores through three practical applications: (i) explaining black-box RL agents by identifying strategically linked pairs among decisions they make, (ii) improving the worst-case performance of decision support systems by distinguishing whether recommended actions can be adopted as standalone improvements or whether they are strategically linked hence requiring a commitment to a broader strategy to be effective, and (iii) characterizing the planning processes of non-RL agents purely through interventions aimed at measuring strategic link scores - as an example, we consider a realistic traffic simulator and analyze through road closures the effective planning horizon of the emergent routing behavior of many drivers.

To provide these metrics, it is necessary find the set of loops on which to compute them. We show in this paper the necessity of including loops that are important at different points in the simulation. These important loops may not be independent of one another and cannot be determined from static analysis of the model structure. We then describe an algorithm that can be used to discover the most important loops in models that are too feedback rich for exhaustive loop discovery. We demonstrate the use of this algorithm in terms of its ability to find the most explanatory loops, and its computational performance for large models. By using this approach, the Loops that Matter method can be applied to models of any size or complexity.

By: William Schoenberg (University of Bergen, Norway) Abstract This work re presents a new approach which generates then analyzes a highly non - linear complex system of differential equations to do interpretable time series forecasting at a high level of accuracy. This approach provides insight and understanding into the mechanisms responsible for gener ating past and future behavior. Core to this method is the construction of a highly non - linear complex system of differential equations that is then analyzed to determine the origins of behavior. This paper demonstrates the technique on Mass and Senge's two state Inventory Workforce model ( 1975) and then explores its application to the real world problem of organogenesis in mice . The organogenesis application consists of a fourteen - state system where the generated set of equations reproduces observed behavior with a high level of accuracy ( 0.88 0 Introduction: Accurate time series forecasting is very important to a variety of scientific fields, engineering disciplines, and socially constructed systems including businesses, and governments (Palit & Popovic, 2006) . Past effort s on this problem have focused on developing more accurate methods or models useful for predicting time series data, starting with linear statistical models and evolving into non - linear models and ultimately machine learning techniques (Bontempi, et, al, 2012) .