Jesper Blynel’s research while affiliated with Eawag: Das Wasserforschungs-Institut des ETH-Bereichs and other places

This paper explores the capabilities of continuous time recur- rent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double T-Maze navigation tasks, where the robot has to locate and "remember" the position of a reward-zone. The "learning" comes about without modifications of synapse strengths, but simply from internal network dynamics, as proposed by (12). Neural controllers are evolved in simulation and in the simple case evaluated on a real robot. The evolved controllers are analyzed and the results obtained are discussed.

In (8) Yamauchi and Beer explored the abilities of continu- ous time recurrent neural networks (CTRNNs) to display reinforcement- learning like abilities. The investigated tasks were generation and learn- ing of short bit sequences. This "learning" came about without mod- ifications of synaptic strengths, but simply from internal dynamics of the evolved networks. In this paper this approach will be extended to two embodied agent tasks, where simulated robots have acquire and retain "knowledge" while moving around dierent mazes. The evolved controllers are analyzed and the results are discussed.

We describe a model and implementation of evolutionary spiking neurons for embedded microcontrollers with few bytes of memory and very low power consumption. The approach is tested with an autonomous microrobot of less than 1 in3 that evolves the ability to move in a small maze without human intervention and external computers. Considering the very large diffusion, small size, and low cost of embedded microcontrollers, the approach described here could find its way in several intelligent devices with sensors and/or actuators, as well as in smart credit cards.

Two classes of dynamical recurrent neural networks, Continuous Time Recurrent Neural Networks (CTRNNs) (Yamauchi and Beer, 1994) and Plastic Neural Networks (PNNs) (Floreano and Urzelai, 2000) are compared on two behavioral tasks aimed at exploring their capabilities to display reinforcement-learning like behaviors and adaptation to unpredictable environmental changes. The networks report similar performances on both tasks, but PNNs display significantly better performance when sensory-motor re-adaptation is required after the evolutionary process. These results are discussed in the context of behavioral, biological, and computational definitions of learning.

Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior The Simulation of Adaptive Behavior Conference brings together researchers from ethology, psychology, ecology, artificial intelligence, artificial life, robotics, computer science, engineering, and related fields to further understanding of the behaviors and underlying mechanisms that allow adaptation and survival in uncertain environments. The work presented focuses on robotic and computational experimentation with well-defined models that help to characterize and compare alternative organizational principles or architectures underlying adaptive behavior in both natural animals and synthetic animats. Bradford Books imprint

We describe a model and implementation of evolutionary spiking neurons for embedded microcontrollers with few bytes of memory and very low power consumption. The approach is tested with an autonomous microrobot of less than 1 in^3 that evolves the ability to move in a small maze without human intervention and external computers. Considering the very large diffusion, small size, and low cost of embedded microcontrollers, the approach described here could find its way in several intelligent devices with sensors and/or actuators, as well as in smart credit cards.