Journal ArticleDOI
Incremental Evolution of Complex General Behavior
Faustino Gomez,Risto Mikkulainen +1 more
TLDR
This article proposes an approach wherein complex general behavior is learned incrementally, by starting with simpler behavior and gradually making the task more challenging and general, which evolves more effective and more general behavior.Abstract:
Several researchers have demonstrated how complex action sequences can be learned through neuroevolution (i.e., evolving neural networks with genetic algorithms). However, complex general behavior such as evading predators or avoiding obstacles, which is not tied to specific environments, turns out to be very difficult to evolve. Often the system discovers mechanical strategies, such as moving back and forth, that help the agent cope but are not very effective, do not appear believable, and do not generalize to new environments. The problem is that a general strategy is too difficult for the evolution system to discover directly. This article proposes an approach wherein such complex general behavior is learned incrementally, by starting with simpler behavior and gradually making the task more challenging and general. The task transitions are implemented through successive stages of Delta coding (i.e., evolving modifications), which allows even converged populations to adapt to the new task. The method is...read more
Citations
More filters
Journal ArticleDOI
Machine learning
TL;DR: Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis.
Journal ArticleDOI
Evolving neural networks through augmenting topologies
TL;DR: Neural Evolution of Augmenting Topologies (NEAT) as mentioned in this paper employs a principled method of crossover of different topologies, protecting structural innovation using speciation, and incrementally growing from minimal structure.
Journal ArticleDOI
Abandoning objectives: Evolution through the search for novelty alone
Joel Lehman,Kenneth O. Stanley +1 more
TL;DR: In the maze navigation and biped walking tasks in this paper, novelty search significantly outperforms objective-based search, suggesting the strange conclusion that some problems are best solved by methods that ignore the objective.
Book ChapterDOI
Evolving Deep Neural Networks
Risto Miikkulainen,Jason Zhi Liang,Elliot Meyerson,Aditya Rawal,Fink Daniel E,Olivier Francon,Bala Raju,Hormoz Shahrzad,Arshak Navruzyan,Nigel Duffy,Babak Hodjat +10 more
TL;DR: An automated method, CoDeepNEAT, is proposed for optimizing deep learning architectures through evolution by extending existing neuroevolution methods to topology, components, and hyperparameters, which achieves results comparable to best human designs in standard benchmarks in object recognition and language modeling.
Journal ArticleDOI
Neuroevolution: from architectures to learning
TL;DR: This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.
References
More filters
Journal ArticleDOI
Machine learning
TL;DR: Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis.
Journal ArticleDOI
Technical Note : \cal Q -Learning
Chris Watkins,Peter Dayan +1 more
TL;DR: This paper presents and proves in detail a convergence theorem forQ-learning based on that outlined in Watkins (1989), showing that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.
Book
A robust layered control system for a mobile robot
TL;DR: A new architecture for controlling mobile robots is described, building a robust and flexible robot control system that has been used to control a mobile robot wandering around unconstrained laboratory areas and computer machine rooms.
Journal ArticleDOI
A robust layered control system for a mobile robot
TL;DR: In this paper, a new architecture for controlling mobile robots is described, which is made up of asynchronous modules that communicate over low-bandwidth channels, each module is an instance of a fairly simple computational machine.
Journal ArticleDOI
Neuronlike adaptive elements that can solve difficult learning control problems
TL;DR: In this article, a system consisting of two neuron-like adaptive elements can solve a difficult learning control problem, where the task is to balance a pole that is hinged to a movable cart by applying forces to the cart base.