Action rule induction from cause-effect pairs learned through robot-teacher interaction

In this work we propose a decision-making system that efficiently learns behaviors in the form of rules using natural human instructions about cause-effect relations in currently observed situations, avoiding complicated instructions and explanations of long-run action sequences and complete world dynamics. The learned rules are represented in a way suitable to both reactive and deliberative approaches, which are thus smoothly integrated. Simple and repetitive tasks are resolved reactively, while complex tasks would be faced in a more deliberative manner using a planner module. Human interaction is only required if the system fails to obtain the expected results when applying a rule, or fails to resolve the task with the knowledge acquired so far. I. INTRODUCTION N this work we are facing the problem of decision making for a multitask robot embedded in a human environment that should rapidly learn to perform tasks by interacting with humans, in an on-line way, and without any previous knowledge of the world dynamics or the tasks to be performed. From a very general point of view, we must consider two alternative approaches to the goal of building an intelligent agent: the deliberative and the reactive approaches. The deliberative approach began with the very birth of AI, and it is based on the principle of rationality (1), which states that "If an agent has knowledge that one of its actions will lead to one of its goals, then the agent will select that action.". The proponents of the knowledge-based systems using the principle of rationality soon realized that there are a number of important shortcomings with this approach, ranging from the frame problem (2), the difficulty of building a large enough database of knowledge providing the grounds for common sense, and the theorems stating the complexity of planning for even some of the simplest kinds of logical problems.