We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...
Recent scaling up of decentralized partially observable Markov decision process (DEC-POMDP) solvers towards realistic applications is mainly due to approximate methods. Of this fa...
Generic representatives have been proposed for the effective combination of symmetry reduction and symbolic representation with BDDs in non-probabilistic model checking. This appro...
Recent research in multi-robot exploration and mapping has focused on sampling environmental fields, which are typically modeled using the Gaussian process (GP). Existing informa...
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....