AMLSI: A Novel Accurate Action Model Learning Algorithm

International audienceThis paper presents a new algorithm based on grammar induction, called AMLSI (Action Model Learning with State machine Interactions), to learn PDDL domains by querying the system to model with action sequences and by observing the state transitions. AMLSI takes as input a training set of feasible and infeasible action sequences built from partial and noisy observations and returns a PDDL domain. A key issue for domain learning is the ability to plan with the learned domains. It often happens that a small learning error leads to a domain that is unusable for planning. Unlike other algorithms, we show that AMLSI is able to lift this lock by learning domains from partial and noisy observations with sufficient accuracy to allow planners to solve new problems