We introduce the value iteration network (VIN): a fully differentiable neural network with a ‘planning module’ embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiable approximation of the value-iteration algorithm, which can be represented a...

In this paper we introduce a novel approach for unsupervised classification of planning instances based on the recent formalism of planning programs. Our approach is inspired by structured prediction in machine learning, which aims at predicting structured information about a given input rather than a scalar value. In our case, each input is an unlabelled classical planning instance, and the as...

A new approach to military planning and execution has been proposed. This approach seeks to merge planning and execution, and replaces reaction to events with anticipation of events. Anticipatory Planning can benefit from automation. This paper presents a methodology for building an automated system to support Anticipatory Planning. A Plan Description is developed to manage the many branches th...

This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose methodology to quickly predict expected tactical descriptions operational solutions (TDOSs). The problem address occurs in context two-stage stochastic programming where second stage is demanding computationally. We aim high speed TDOS associated with problem, cond...

Predicting a defect inflow is important for project planning and monitoring purposes. For project planning purposes and for quality management purposes, an important measure is the trend of defect inflow in the project – i.e. how many defects are reported in a particular stage of the project. Predicting the defect inflow provides a mechanism of early notification whether the project is going to...

Recent studies have highlighted cognitive and neural similarities between planning and perceiving actions. Given that action planning involves a simulation of potential action plans that depends on the actor's body posture, we reasoned that perceiving actions may also be influenced by one's body posture. Here, we test whether and how this influence occurs by measuring behavioral and cerebral (f...

more than 50% of the global population already lives in urban settlements which are projected to absorb almost all the global population growth to 2050, amounting to some additional three billion people. over the next decades the increase in rural population in many developing countries will be overshadowed by population flows to cities. rural populations globally are expected to peak at a leve...