Filters








6,548 Hits in 2.8 sec

Special issue on the 20th anniversary of XCS

Tim Kovacs, Muhammad Iqbal, Kamran Shafi, Ryan Urbanowicz
2015 Evolutionary Intelligence  
[9] introduced XCSAM (XCS with Adaptive action Mapping), which estimates how often each rule takes an optimal action and incorporates that estimate into the rule's fitness.  ...  The fact that the map is complete allows XCS to learn about every state/action combination, which is an advantage in RL tasks given the typical uncertainty about which action is best for a given state.  ... 
doi:10.1007/s12065-015-0131-0 fatcat:2f52bxzpzfd77hz3je26azrtei

Revisit of Rule-Deletion Strategy for XCSAM Classifier System on Classification

Masaya Nakata, Tomoki Hamagami
2017 Transactions of the Institute of Systems Control and Information Engineers  
This paper starts with claiming a limitation that XCSAM still fails to evolutionary generate adequate rules advocating the highest-return actions.  ...  The XCSAM classifier system is an approach of evolutionary rule-based machine learning, which evolves rules advocating the highest-return actions at state, resulting in best classification.  ...  And so XCSAM-DS averagely performs with a smaller θ mna than XCS. Hence, XCSAM-DS builds the best action map with fewer redundant rules than XCSAM, i.e., building the best action map successfully.  ... 
doi:10.5687/iscie.30.273 fatcat:eba2jzyvszdabfeqwyllsflp44

Self-adaptive constructivism in Neural XCS and XCSF

Gerard D. Howard, Larry Bull, Pier-Luca Lanzi
2008 Proceedings of the 10th annual conference on Genetic and evolutionary computation - GECCO '08  
For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability.  ...  In this sense adaptability includes representational flexibility guided by the environment at any given time.  ...  For clarities' sake, we shall refer to the four systems presented using the following nomenclature: non-adaptive N-XCS (naN-XCS), self-adaptive N-XCS (saN-XCS), neural constructive and self-adaptive XCS  ... 
doi:10.1145/1389095.1389364 dblp:conf/gecco/HowardBL08 fatcat:mlc63vrhfnc5jbzbsrjjnj6m2i

Revisiting UCS: Description, Fitness Sharing, and Comparison with XCS [chapter]

Albert Orriols-Puig, Ester Bernadó-Mansilla
2008 Lecture Notes in Computer Science  
Results show the benefits of fitness sharing in all the tested problems, specially those with class imbalances. Comparison with XCS highlights the dynamics differences between both systems.  ...  Also XCS is included in the comparison to analyze the differences in behavior between both systems.  ...  Proportion of the best action map achieved by UCSns, UCSs, and XCS in the 20-bit multiplexer with alternating noise and with configurations C alt 1 , C alt 2 , and C alt 3 Table 3 . 3 Best action map  ... 
doi:10.1007/978-3-540-88138-4_6 fatcat:57dlbeq7k5bx7nzlqs267issdi

Context-Aware Mobile Service Adaptation via a Co-Evolution eXtended Classifier System in Mobile Network Environments

Shangguang Wang, Zibin Zheng, Zhengping Wu, Qibo Sun, Hua Zou, Fangchun Yang
2014 Mobile Information Systems  
We compare CXCS based on a common mobile service adaptation scenario with other five adaptation schemes.  ...  With the popularity of mobile services, an effective context-aware mobile service adaptation is becoming more and more important for operators.  ...  In this paper, the user context can be mapped to the classifier conditions, and mobile services can be mapped to classifier actions.  ... 
doi:10.1155/2014/890891 fatcat:yiveq7ax6vdbdd5pv7okxicuz4

An Empirical Analysis of Action Map in Learning Classifier Systems

Masaya NAKATA, Keiki TAKADAMA
2018 SICE Journal of Control Measurement and System Integration  
This paper attempts to empirically conclude this issue with an intensive analysis comparing different action maps on LCSs.  ...  It still remains unclear which action map can be adequate to solve which type of problem effectively, resulting in a lack of basic design methodology of LCS in terms of the action map.  ...  We introduced a basic LCS model called the XCS with adaptive action mapping (XCSAM) classifier system [12] , which employs the same reinforcement learning technique of XCS but uses the option of the best  ... 
doi:10.9746/jcmsi.11.239 fatcat:y4hnbkw34jaazlowfa22oltjta

Intrusion detection with evolutionary learning classifier systems

Kamran Shafi, Tim Kovacs, Hussein A. Abbass, Weiping Zhu
2007 Natural Computing  
Moreover, it demands high accuracy, fast processing times and adaptability to a changing environment.  ...  Evolutionary Learning Classifier Systems (LCSs) combine reinforcement learning or supervised learning with effective genetics-based search techniques.  ...  Next in Sect. 6 we altered covering in XCS in an attempt to replace its complete maps with best action maps but found little effect. .  ... 
doi:10.1007/s11047-007-9053-9 fatcat:hwjdqhdph5gq3b3xo3a4apyu2y

Active Reinforcement Learning – A Roadmap Towards Curious Classifier Systems for Self-Adaptation [article]

Simon Reichhuber, Sven Tomforde
2022 arXiv   pre-print
In this context, the fundamental reinforcement learning approaches come with several drawbacks that hinder their application to real-world systems: trial-and-error, purely reactive behaviour or isolated  ...  Figure 6 : 6 Figure 6: Self-adaptive XCS with observer/controller tasks.  ...  It can not be mapped directly to the evaluation criteria of XCS, since there is no individual 'value' of a classifier.  ... 
arXiv:2201.03947v1 fatcat:6dgept56bfg2bdiqvvlrlm6ha4

Rule Fitness and Pathology in Learning Classifier Systems

Tim Kovacs
2004 Evolutionary Computation  
We begin with the basics, considering definitions for correct and incorrect actions, and then correct, incorrect, and overgeneral rules for both strength and accuracy-based fitness.  ...  In contrast, the more recent accuracy-based XCS, appears both to adapt and generalise well. In this work, we attribute the difference to what we call strong over general and fit over general rules.  ...  This is compatible with forming a best action map, so E is not overgeneral.  ... 
doi:10.1162/106365604773644341 pmid:15096307 fatcat:amt7ba5io5dp3nx6psfiokf24y

Rule Fitness and Pathology in Learning Classifier Systems

Tim Kovacs
2004 Evolutionary Computation  
We begin with the basics, considering definitions for correct and incorrect actions, and then correct, incorrect, and overgeneral rules for both strength and accuracy-based fitness.  ...  In contrast, the more recent accuracy-based XCS, appears both to adapt and generalise well. In this work, we attribute the difference to what we call strong over general and fit over general rules.  ...  This is compatible with forming a best action map, so E is not overgeneral.  ... 
doi:10.1162/evco.2004.12.1.99 pmid:15096307 fatcat:4th7w4gggffevkv73gaj2dvw2u

Accuracy-Based Learning Classifier Systems: Models, Analysis and Applications to Classification Tasks

Ester Bernadó-Mansilla, Josep M. Garrell-Guiu
2003 Evolutionary Computation  
Departing from XCS, we analyze the evolution of a complete action map as a knowledge representation. We propose an alternative, UCS, which evolves a best action map more efficiently.  ...  While XCS bases fitness on a reinforcement learning scheme, UCS defines fitness from a supervised learning scheme.  ...  The size of a complete action map is greater than a best action map. In a categorization problem with classes, a complete action map can be as much as times larger than the best action map.  ... 
doi:10.1162/106365603322365289 pmid:14558911 fatcat:25wu53rxhbe27mzk5li6nmvs3a

Self-adaptation of parameters in a learning classifier system ensemble machine

Maciej Troć, Olgierd Unold
2010 International Journal of Applied Mathematics and Computer Science  
A new self-adaptive XCS-based ensemble machine was compared with two other XCS-based ensembles in relation to one-step binary problems: Multiplexer, One Counts, Hidden Parity, and randomly generated Boolean  ...  Several research works have tried to deal with this problem; however, the construction of algorithms letting the parameters adapt themselves to the problem is a critical and open problem of EAs.  ...  Therefore, adapting the XCS system relies on building a "payoff map" of the environment in which the system acts (Butz et al., 2004) .  ... 
doi:10.2478/v10006-010-0012-8 fatcat:alquaw4n5jgwfk5y2e2mzonakm

Learning from Data using XCS

Elias B. Ayele, Abdollah Homaifar, Albert Esterline, Robert Dean, Dan Rodgers
2008 IFAC Proceedings Volumes  
The sample application, the Terrain Reasoner Weight Adapter (TRWA), is a system that learns near optimal weights to be used by a path planner while generating routes.  ...  The results obtained show the efficiency of the method. 1 Butz and Wilson (2001) details the XCS algorithm.  ...  p i i F i (1) The XCS chooses an action from those present in [M ] .  ... 
doi:10.3182/20080706-5-kr-1001.02613 fatcat:2d7qotypazcjzbqss2wl6sujqi

Parameter Adaptation within Co-adaptive Learning Classifier Systems [chapter]

Chung-Yuan Huang, Chuen-Tsai Sun
2004 Lecture Notes in Computer Science  
The system combines the advantages of both adaptive and self-adaptive parameter-control approaches.  ...  The authors propose a co-adaptive approach to controlling parameters for coevolution-based learning classifier systems.  ...  Meta-XCS integrates Dyna architecture with XCSµ [7, 8] , which is especially useful in stochastic environments where the results of actions are affected by uncertainty.  ... 
doi:10.1007/978-3-540-24855-2_92 fatcat:xxzbwm3hvrcsjcog7ikgu2sheu

Classifier Fitness Based on Accuracy

Stewart W. Wilson
1995 Evolutionary Computation  
These aspects of XCS result in its population tending to form a complete and accurate mapping X x A + P from inputs and actions to payoff predictions.  ...  Further, XCS tends to evolve classifiers that are maximally general, subject to an accuracy criterion.  ...  Experiments with XCS Generalization Hypothesis As noted in Section 2, our intention with XCS was to form accurate maps of the X x A 3 P space, or payoff landscape, of the problem.  ... 
doi:10.1162/evco.1995.3.2.149 fatcat:h5t5olb5pjbi3nn25oxahl3zcy
« Previous Showing results 1 — 15 out of 6,548 results