Intelligent Agents with Reinforcement Learning and Fuzzy logic for Intention commitment Modeling

We present a new h-BD[I] architecture that enables an improved decision making features in dynamic, and complex environments. Paper discusses the present limitations of BDI (belief desire-intention) agent model and proposes a new extended architecture, h-BD[I] for non deterministic, dynamic environments. The lack of learning competences and difficulties in dealing with vague or imprecise data sets in the environment are the main obstacles in finding an optimal solution in the present BDI model. We present three different types of commitment strategies namely, "single-option-short-sighted" (SOSS), "single-option-far-sighted" (SOFS) and "multi-option-far-sighted" (MOFS) for improved behavior in the proposed model