Proceedings Article10.1145/2739480.2754732
Evolutionary Bilevel Optimization for Complex Control Tasks
Jason Zhi Liang,Risto Miikkulainen +1 more
- 11 Jul 2015
- pp 871-878
32
TL;DR: A novel method called MetaEvolutionary Algorithm (MEA) is presented and shown to be capable of efficiently discovering optimal parameters for neuroevolution to solve control problems.
read more
Abstract: Most optimization algorithms must undergo time consuming parameter adaptation in order to optimally solve complex, real-world control tasks. Parameter adaptation is inherently a bilevel optimization problem where the lower level objective function is the performance of the control parameters discovered by an optimization algorithm and the upper level objective function is the performance of the algorithm given its parametrization. In this paper, a novel method called MetaEvolutionary Algorithm (MEA) is presented and shown to be capable of efficiently discovering optimal parameters for neuroevolution to solve control problems. In two challenging examples, double pole balancing and helicopter hovering, MEA discovers optimized parameters that result in better performance than hand tuning and other automatic methods. Bilevel optimization in general and MEA in particular, is thus a promising approach for solving difficult control tasks.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
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.
1.1K
A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications
TL;DR: A comprehensive review on bilevel optimization from the basic principles to solution strategies is provided in this paper, where a number of potential application problems are also discussed and an automated text-analysis of an extended list of papers has been performed.
907
•Posted Content
A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications.
TL;DR: An automated text-analysis of an extended list of papers published on bilevel optimization from the basic principles to solution strategies; both classical and evolutionary is performed.
268
•Journal Article
Efficient non-linear control through neuroevolution
TL;DR: In this article, a novel neuroevolution method called CoSyNE that evolves networks at the level of weights was introduced for the pole-balancing problem, which was tested in difficult versions of the pole balancing problem.
137
Evolving deep neural networks
Risto Miikkulainen,Jason Liang,Elliot Meyerson,Aditya Rawal,Dan Fink,Olivier Francon,Bommena Raju,Hormoz Shahrzad,Arshak Navruzyan,Nigel Duffy,Babak Hodjat +10 more
- 01 Jan 2024
TL;DR: Evolving deep neural networks is a promising approach to constructing deep learning applications by automating architecture optimization through evolution.
101
References
Random Forests
Leo Breiman
- 01 Oct 2001
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
•Book
Reinforcement Learning: An Introduction
Richard S. Sutton,Andrew G. Barto +1 more
- 01 Jan 1988
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
•Book
Handbook of Genetic Algorithms
Lawrence Davis
- 01 Jan 1991
TL;DR: This book sets out to explain what genetic algorithms are and how they can be used to solve real-world problems, and introduces the fundamental genetic algorithm (GA), and shows how the basic technique may be applied to a very simple numerical optimisation problem.
8.2K
Evolving artificial neural networks
Xin Yao
- 01 Sep 1999
TL;DR: It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.
Optimization of Control Parameters for Genetic Algorithms
John J. Grefenstette
- 01 Jan 1986
TL;DR: GA's are shown to be effective for both levels of the systems optimization problem and are applied to the second level task of identifying efficient GA's for a set of numerical optimization problems.
3.1K