We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...
Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speec...
This paper extends the framework of dynamic influence diagrams (DIDs) to the multi-agent setting. DIDs are computational representations of the Partially Observable Markov Decisio...
The search for finite-state controllers for partially observable Markov decision processes (POMDPs) is often based on approaches like gradient ascent, attractive because of their ...
A problem of planning for cooperative teams under uncertainty is a crucial one in multiagent systems. Decentralized partially observable Markov decision processes (DECPOMDPs) prov...