Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...
Planning methods for deterministic planning problems traditionally exploit factored representations to encode the dynamics of problems in terms of a set of parameters, e.g., the l...
Partially Observable Markov Decision Processes (POMDPs) provide a general framework for AI planning, but they lack the structure for representing real world planning problems in a...
Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually in...
Predictive State Representations (PSRs) have shown a great deal of promise as an alternative to Markov models. However, learning a PSR from a single stream of data generated from ...