Learning classifier systems: then and now

@article{Lanzi2008LearningCS,
  title={Learning classifier systems: then and now},
  author={Pier Luca Lanzi},
  journal={Evolutionary Intelligence},
  year={2008},
  volume={1},
  pages={63-82}
}
  • P. Lanzi
  • Published 8 February 2008
  • Computer Science
  • Evolutionary Intelligence
Broadly conceived as computational models of cognition and tools for modeling complex adaptive systems, later extended for use in adaptive robotics, and today also applied to effective classification and data-mining–what has happened to learning classifier systems in the last decade? This paper addresses this question by examining the current state of learning classifier system research. 
Developing an evolvable pattern generator using learning classifier systems
TLDR
A novel problem domain has been created that can be manipulated autonomously (i.e. scalable and evolvable patterns) to benefit autonomous systems and confirm that both the problem domain can be evolved and the problem solutions can be learnt lowering the requirement of human intervention in developing autonomous systems.
Learning Classifier System Improvement Based on Probability Driven and Neural Network Driven Approaches
  • Ladislav Clementis
  • Computer Science
    2013 3rd Eastern European Regional Conference on the Engineering of Computer Based Systems
  • 2013
TLDR
This work provides modified Learning Classifier System enriched by probability model to help build an appropriate knowledge base more effectively and included a neural network into the action selection process and therefore action can be determined accordingly with a probability model.
Learning Classifier System on a humanoid NAO robot in dynamic environments
TLDR
A modified version of Extended Classifier System (XCS) on a humanoid NAO robot is presented which demonstrates the desirable adaptivity of LCS for a sequential task on a real robot in dynamic environments.
Using Learning Classifier Systems to Learn
TLDR
Two new learning systems based on a regular gradient learning technology and a new natural gradient learning method are developed that clearly shows that LCSs provide a suitable platform for efficient and reliable learning of stochastic policies.
Learning Classifier Systems: Looking Back and Glimpsing Ahead
TLDR
A look back at the LCS field is provided, whereby the emphasis is placed on the recent advances, and a glimpse ahead is taken by discussing future challenges and opportunities for successful system applications in various domains.
TO BOUND SEARCH SPACE AND BOOST PERFORMANCE OF LEARNING CLASSIFIER SYSTEMS : A ROUGH SET APPROACH
Learning classifier system is a machine learning technique which combines genetic algorithm with the power of the reinforcement learning paradigm. This rule based system has been inspired by the
Using Learning Classifier Systems to Learn Stochastic Decision Policies
TLDR
This paper has developed two new learning systems, one based on a regular gradient learning technology and the otherbased on a new natural gradient learning method, which clearly shows that LCSs provide a suitable platform for efficient and reliable learning of stochastic policies.
How should learning classifier systems cover a state-action space?
TLDR
The learning strategy improves the stability of XCS performance compared with the existing strategies on all types of noise employed in this paper, and supports that claim that existing learning strategies have dependencies on the types of Noise in reinforcement learning problems.
A brief history of learning classifier systems: from CS-1 to XCS and its variants
  • L. Bull
  • Computer Science
    Evol. Intell.
  • 2015
TLDR
This paper gives an overview of the evolution of Learning Classifier Systems up to XCS, and of some of the subsequent developments of Wilson’s algorithm to different types of learning.
An Improved Continuous-Action Extended Classifier Systems for Function Approximation
TLDR
An improved XCS with continuous actions is introduced for function approximation purposes and is shown to produce more accurate rules than the classical classifier system when it comes to approximating complex nonlinear functions.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 247 REFERENCES
X-TCS: accuracy-based learning classifier system robotics
  • M. Studley, L. Bull
  • Computer Science
    2005 IEEE Congress on Evolutionary Computation
  • 2005
TLDR
Initial results from an extension of XCS that operates in continuous environments on a physical robot is presented and it is shown to be capable of near optimal performance in a simple robotic task.
Classifier systems that compute action mappings
TLDR
A version of XCS with computed actions, briefly XCSCA, that can be applied to problems involving a large number of actions and can evolve accurate and compact representations of binary functions which would be challenging for typical learning classifier system models is introduced.
Building anticipations in an accuracy-based learning classifier system by use of an artificial neural network
TLDR
This paper presents a mechanism by which to create learning classifier systems of this type, here using accuracy-based fitness, and highlights the supervised learning nature of the anticipatory task and amend each rule of the system with a traditional artificial neural network.
Cognitive systems based on adaptive algorithms
TLDR
The type of cognitive system studied here has a set of interacting elementary productions, called classifiers, and a performance algorithm that directs the action of the system in the environment and modifies the set of classifiers so that variants of good classifiers persist and new, potentially better ones are created in a provably efficient manner.
A Critical Review of Classifier Systems
TLDR
This work presents a kind of rule-based system with general mechanisms for processing rules in parallel, for adaptive generation of new rules, and for testing the effectiveness of existing rules.
Genetics-based machine learning and behavior-based robotics: a new synthesis
TLDR
Experiments show how behavior acquisition can be achieved by means of a learning coordination mechanism using an architecture based on learning classifier systems and on the structural properties of animal behavioral organization as proposed by ethologists.
A Roadmap to the Last Decade of Learning Classifier System Research
TLDR
This paper reviews the subsequent ten years of learning classifier systems research discussing the main achievements and the major research directions pursued in those years.
Combining latent learning with dynamic programming in the modular anticipatory classifier system
TLDR
This paper describes how the model can be used to perform active exploration and how this exploration may be aggregated with the policy resulting from the reinforcement learning process, and proposes a new system, called Modular Anticipatory Classifier System (MACS), which allows the latent learning process to take advantage of new regularities.
A Self-adaptive Neural Learning Classifier System with Constructivism for Mobile Robot Control
TLDR
It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task.
Anticipation mappings for learning classifier systems
TLDR
This paper applies XCS with anticipation mappings (XCSAM) to several multistep problems taken from the literature and compares its anticipatory performance with that of the neural classifier system X-NCS which is based on a similar approach.
...
1
2
3
4
5
...