Exploring the T-Maze: evolving learning-like robot behaviors using CTRNNs

Authors:
Jesper Blynel;Dario Floreano
Affiliations:
Autonomous Systems Lab, Institute of Systems Engineering, Swiss Federal Institute of Technology, Lausanne, Switzerland;Autonomous Systems Lab, Institute of Systems Engineering, Swiss Federal Institute of Technology, Lausanne, Switzerland
Venue:
EvoWorkshops'03 Proceedings of the 2003 international conference on Applications of evolutionary computing
Year:
2003

Citing 11
Cited 11

Sequential behavior and learning in evolved dynamical neural networks

Adaptive Behavior
Integrating reactive, sequential, and learning behavior using dynamical neural networks

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Evolutionary robotics and the radical envelope-of-noise hypothesis

Adaptive Behavior
Understanding intelligence

Understanding intelligence
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

Neural Networks - Special issue on organisation of computation in brain-like systems
Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Levels of dynamics and adaptive behavior in evolutionary neural controllers

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Evolving integrated controllers for autonomous learning robots using dynamic neural networks

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Evolving mobile robots in simulated and real environments

Artificial Life
Evolving reinforcement learning-like abilities for robots

ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Model-based learning for mobile robot navigation from the dynamicalsystems perspective

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

The Dynamics of Associative Learning in Evolved Model Circuits

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Evolution of Signaling in a Multi-Robot System: Categorization and Communication

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Swarm robotics and minimalism

Connection Science
Associative Learning on a Continuum in Evolved Dynamical Neural Networks

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Novelty of behaviour as a basis for the neuro-evolution of operant reward learning

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Exploring multi-objective evolution of robot brains in obstacle and maze environments with varying complexities

ACST '08 Proceedings of the Fourth IASTED International Conference on Advances in Computer Science and Technology
Indirectly encoding neural plasticity as a pattern of local rules

SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Evolving plastic neural networks with novelty search

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Emergence of memory in neuroevolution: impact of selection pressures

Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Evolving spiking networks with variable resistive memories

Evolutionary Computation
Discrimination learning guided by instinct

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper explores the capabilities of continuous time recurrent 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.