Serin Lee, Takashi Kubota, and Ichiro Nakatani
The approaches to make an agent generate intelligent actions in the field of AI might be very roughly categorized into two ways—the classical planning and situated action system. It is well known that each system has its own strength and weakness. However, each system also has its own application field. In particular, most of situated action systems do not directly deal with the logical problem. This paper proposes a novel action generator to situatedly extract a set of actions, which is likely to help to achieve the goal at the current situation, by the noop first heuristic in the relaxed logical space. After performing the set of actions, the agent should recognize the situation for deciding the next likely set of actions. The empirical result in some planning domains shows that the quality of the resultant path to the goal, post-hoc reconstruction of plans, is mostly acceptable as well as deriving the fast response time.