In planning search, there are different approaches to guide the search, where all of them are focused in have a plan (solution) in less time. Most of the researches are not admissible heuristics, but they have good results in time. For example, using the heuristic-search planning approach plans can be generated in less time than other approaches, but the plans generated by all heuristic planners are sub-optimal, or could have dead ends (states from which the goals get unreachable). We present an approach to guide the search in a probabilistic way in order to do not have the problems of the not admissible approaches. We extended the Bayesian network and Bayesian inferences ideas to our work. Furthermore, we present our way to make Bayesian inferences in order to guide the search in a better way. The results of our experiments of our approach with different well-known benchmarks are presented. The benchmarks used in our experiments are: Driverlog, Zenotravel, Satellite, Rovers, and Freecell.
