Regret based algorithms have been proposed to control a wide variety of multi-agent systems. The appeal of regretbased algorithms is that (1) these algorithms are easily implement...
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...
We present a new approximation algorithm based on an exact representation of the state space S, using decision diagrams, and of the transition rate matrix R, using Kronecker algeb...
Andrew S. Miner, Gianfranco Ciardo, Susanna Donate...
We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...