We combined a spoken dialog system that we developed to deliver brief health interventions with the fully aut onomous humanoid robot (NAO). The dialog system is based on a framework facilitating Markov decision processes (MDP). It is optimized using reinforcement learning (RL) algorithms with data we collected from real user interactions. The system begins to learn optim al dialog strategies for initiative selection and for the type of confirmations that it uses during the interaction. The health intervention, delivered by a 3D character ins tead of the NAO, has already been evaluated, with posit ive results in terms of task completion, ease of use, and future intention to use the system. The current spoken dialog system for the humanoid robot is a novelty and exists so far as a proof of concept.
