File(s) not publicly available
An evolutionary ecological approach to the study of learning behaviour using a robot based model
journal contributionposted on 2023-06-07, 21:03 authored by Elio Tuci, Matt Quinn, Inman HarveyInman Harvey
We are interested in the construction of ecological models of the evolution of learning behaviour using methodological tools developed in the field of evolutionary robotics. In this paper, we explore the applicability of integrated (i.e., non-modular) neural networks with fixed connection weights and simple "leaky-integrator" neurons as controllers for autonomous learning robots. In contrast to Yamauchi and Beer (1994a), we show that such a control system is capable of integrating reactive and learned behaviour without needing explicitly hand-designed modules, dedicated to particular behaviour, or an externally introduced reinforcement signal. In our model, evolutionary and ecological contingencies structure the controller and the behavioural responses of the robot. This allows us to concentrate on examining the conditions under which learning behaviour evolves.
Department affiliated with
- Informatics Publications
NotesOriginality. Tackles a classical conceptual problem of understanding learning from a novel approach, with learning arising implicitly in the behaviour of a situated agent. Rigour. Second application of Evolutionary Robotics to this specific issue, and this succeeds where the first attempt (Yamauchi and Beer 1994) had serious shortcomings. Significance. Successfully evolved for the first time on this type of problem. Impact: Google Scholar 14 external citations.
Full text available