Untitled

Abstract

Abstract. Agents (hardware or software) that act autonomously in an environment have to be able to integrate three basic behaviors: planning, execution, and learning. This integration is mandatory when the agent has no knowledge about how its actions can affect the environment, how the environment reacts to its actions, or, when the agent does not receive as an explicit input, the goals it must achieve. Without an "a priori" theory, autonomous agents should be able to self-propose goals, set-up plans for achieving the goals according to previously learned models of the agent and the environment, and learn those models from past experiences of successful and failed executions of plans. Planning involves selecting a goal to reach and computing a set of actions that will allow the autonomous agent to achieve the goal. Execution deals with the interaction with the environment by application of planned actions, observation of resulting perceptions, and control of successful achievement of the goals. Learning is needed to predict the reactions of the environment to the agent actions, thus guiding the agent to achieve its goals more effi iently.In this context, most of the learning systems applied to problem solving have been used to learn control knowledge for guiding the search for a plan, but few systems have focused on the acquisition of planning operator descriptions. As an example, currently, one of the most used techniques for the integration of (a way of) planning, execution, and learning is reinforcement learning. However, they usually do not consider the representation of action descriptions, so they cannot reason in terms of goals and ways of achieving those goals.In this paper, we present an integrated architecture, LOPE, that learns operator def nitions, plans using those operators, and executes the plans for modifying the acquired operators. The resulting system is domain-independent, and we have performed experiments in a robotic framework. The results clearly show that the integrated planning, learning, and executing system outperforms the basic planner in that domain.

Inductive Logic Programming and Embodied Agents

“…Indeed, published critiques of this approach state that it needs "some type of prior background knowledge, either a predefined domain theory in the form of initial operators, or external instruction and knowledge on how to perform the transformation." (Garcia-Martinez et al, 2000) and that "Having an AI designer providing the robots with an adequate representation has a major drawback: it is fixed, ad-hoc representation. Any change of setting (e.g.…”

Prediction in Health Domain Using Bayesian Networks Optimization Based on Induction Learning Techniques

“…The learning can be defined as "any process through as a system improves its efficiency". The ability to learn is considered a central characteristic of the "intelligent systems", 1,2 and for this, a lot of effort and dedication was invested in the investigation and the development of this area. The development of the knowledge based systems motivated the investigation in the area of the learning with the purpose of automating the process of knowledge acquisition which considers one of the main problems in the construction of these systems.…”