Evolving a single scalable controller for an octopus arm with a variable number of segments

Authors:
Brian G. Woolley;Kenneth O. Stanley
Affiliations:
School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL;School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL
Venue:
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part II
Year:
2010

Citing 12
Cited 6

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Evolving neural networks through augmenting topologies

Evolutionary Computation
Creating high-level components with a generative representation for body-brain evolution

Artificial Life
A Taxonomy for artificial embryogeny

Artificial Life
Compositional pattern producing networks: A novel abstraction of development

Genetic Programming and Evolvable Machines
A novel generative encoding for exploiting neural network sensor and output geometry

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Generating large-scale neural networks through discovering geometric regularities

Proceedings of the 9th annual conference on Genetic and evolutionary computation
A hypercube-based encoding for evolving large-scale neural networks

Artificial Life
Competitive coevolution through evolutionary complexification

Journal of Artificial Intelligence Research
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Autonomous evolution of topographic regularities in artificial neural networks

Neural Computation

Evolving neural fields for problems with large input and output spaces

Neural Networks
Block diagonal natural evolution strategies

PPSN'12 Proceedings of the 12th international conference on Parallel Problem Solving from Nature - Volume Part II
Compressed network complexity search

PPSN'12 Proceedings of the 12th international conference on Parallel Problem Solving from Nature - Volume Part I
2013 Special Issue: Autonomous reinforcement learning with experience replay

Neural Networks
Single-unit pattern generators for quadruped locomotion

Proceedings of the 15th annual conference on Genetic and evolutionary computation
Encouraging reactivity to create robust machines

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

While traditional approaches to machine learning are sensitive to highdimensional state and action spaces, this paper demonstrates how an indirectly encoded neurocontroller for a simulated octopus arm leverages regularities and domain geometry to capture underlying motion principles and sidestep the superficial trap of dimensionality. In particular, controllers are evolved for arms with 8, 10, 12, 14, and 16 segments in equivalent time. Furthermore, when transferred without further training, solutions evolved on smaller arms retain the fundamental motion model because they simply extend the general kinematic concepts discovered at the original size. Thus this work demonstrates that dimensionality can be a false measure of domain complexity and that indirect encoding makes it possible to shift the focus to the underlying conceptual challenge.