Title : Logic Production Systems - Introduction and Implementation
| Presenter | Miguel Calejo |
| Abstract | LPS (logic-based production system) is an attempt to implement a unifying framework that is lacking in Computing today, the result of over a decade of research by Kowalski and Sadri. LPS includes both logic programs and reactive rules, which are a logical reconstruction of production system rules. Logic programs in LPS represent the beliefs of an intelligent agent, and reactive rules represent the agent’s goals. Computation in LPS consists in destructively performing state-transforming actions to make consequents true whenever antecedents become true. An open-source, web-based reference implementation of LPS in SWI-Prolog will be demonstrated on a number of examples. The implementation will be overviewed, concluding with opportunities for future work. More information at https://bitbucket.org/lpsmasters/lps_corner. |
Title : Analysis of Lamarckian Evolution for Morphologically Evolving Robots
| Presenter | Milan Jelisavcic |
| Abstract | Evolving robot morphologies implies the need for lifetime learning so that individual robots can learn to manipulate their bodies. An individual’s morphology will obviously combine traits of all its parents; it must adapt its own controller to suit its morphology, and cannot rely on the controller of any one parent to perform well without adaptation. This paper investigates the practicability and benefits of Lamarckian evolution in this setting. Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that com- bines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers. Experimental validation shows that a Lamarckian setup with CPPN-CPG provides substantial benefits. |