Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...
We consider the problem of how to design large decentralized multiagent systems (MAS’s) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a...
The Support Vector Machine (SVM) is an interesting classifier with excellent power of generalization. In this paper, we consider applying the SVM to semi-supervised learning. We p...
Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...