Tuci, Elio, Harvey, Inman and Quinn, Matt (2002) Evolving integrated controllers for autonomous learning robots using dynamic neural networks. In: Proceedings of The Seventh International Conference on the Simulation of Adaptive Behavior (SAB'02), 4-9 August 2002, Edinburgh, UK., Edinburgh.
Full text not available from this repository.Abstract
In 1994, Yamauchi and Beer (1994) attempted to evolve a dynamic neural network as a control system for a simulated agent capable of performaning learned behaviour. They tried to evolve an integrated network, i.e. not modularized; this attempt failed. They ended up having to use independent evolution of separate controller modules, arbitrarily partitioned by the researcher. Moreover, they "provided" the agents with hard-wired reinforcement signals. The model we describe in this paper demonstrates that it is possible to evolve an integrated dynamic neural network that successfully controls the behaviour of a khepera robot engaged in a simple learning task. We show that dynamic neural networks, based on leaky-integrator neuron, shaped by evolution, appear to be able to integrate reactive and learned behaviour with an integrated control system which also benefits from its own reinforcement signal.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Schools and Departments: | School of Engineering and Informatics > Informatics |
Depositing User: | Inman Harvey |
Date Deposited: | 06 Feb 2012 19:52 |
Last Modified: | 13 Apr 2012 10:45 |
URI: | http://sro.sussex.ac.uk/id/eprint/22734 |