Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
Coloring a k-colorable graph using k colors (k ≥ 3) is a notoriously hard problem. Considering average case analysis allows for better results. In this work we consider the unif...
Amin Coja-Oghlan, Michael Krivelevich, Dan Vilench...
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
—Long time-series datasets are common in many domains, especially scientific domains. Applications in these fields often require comparing trajectories using similarity measure...
—We consider an end-to-end approach of inferring probabilistic data-forwarding failures in an externally managed overlay network, where overlay nodes are independently operated b...