Results 1  10
of
62
Improving coevolutionary search for optimal multiagent behaviors
 In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI
, 2003
"... Evolutionary computation is a useful technique for learning behaviors in multiagent systems. Among the several types of evolutionary computation, one natural and popular method is to coevolve multiagent behaviors in multiple, cooperating populations. Recent research has suggested that coevolutionary ..."
Abstract

Cited by 28 (12 self)
 Add to MetaCart
Evolutionary computation is a useful technique for learning behaviors in multiagent systems. Among the several types of evolutionary computation, one natural and popular method is to coevolve multiagent behaviors in multiple, cooperating populations. Recent research has suggested that coevolutionary systems may favor stability rather than performance in some domains. In order to improve upon existing methods, this paper examines the idea of modifying traditional coevolution, biasing it to search for maximal rewards. We introduce a theoretical justification of the improved method and present experiments in three problem domains. We conclude that biasing can help coevolution find better results in some multiagent problem domains. 1
The MaxSolve algorithm for coevolution
 In Beyer, H.G. (Ed.), Proceedings of the Genetic and Evolutionary Computation Conference, GECCO05
, 2005
"... Coevolution can be used to adaptively choose the tests used for evaluating candidate solutions. A longstanding question is how this dynamic setup may be organized to yield reliable search methods. Reliability can only be considered in connection with a particular solution concept specifying what co ..."
Abstract

Cited by 21 (2 self)
 Add to MetaCart
Coevolution can be used to adaptively choose the tests used for evaluating candidate solutions. A longstanding question is how this dynamic setup may be organized to yield reliable search methods. Reliability can only be considered in connection with a particular solution concept specifying what constitutes a solution. Recently, monotonic coevolution algorithms have been proposed for several solution concepts. Here, we introduce a new algorithm that guarantees monotonicity for the solution concept of maximizing the expected utility of a candidate solution. The method, called MaxSolve, is compared to the IPCA algorithm and found to perform more efficiently for a range of parameter values on an abstract test problem.
managed challenge’ alleviates disengagement in coevolutionary system identification
 GECCO 2005: Proceedings of the 2005 conference on Genetic and evolutionary computation
, 2005
"... In previous papers we have described a coevolutionary algorithm (EEA), the estimationexploration algorithm, that infers the hidden inner structure of systems using minimal testing. In this paper we introduce the concept of ‘managed challenge ’ to alleviate the problem of disengagement in this and ..."
Abstract

Cited by 19 (5 self)
 Add to MetaCart
In previous papers we have described a coevolutionary algorithm (EEA), the estimationexploration algorithm, that infers the hidden inner structure of systems using minimal testing. In this paper we introduce the concept of ‘managed challenge ’ to alleviate the problem of disengagement in this and other coevolutionary algorithms. A known problem in coevolutionary dynamics occurs when one population systematically outperforms the other, resulting in a loss of selection pressure for both populations. In system identification (which deals with determining the inner structure of a system using only input/output data), multiple trials (a test that causes the system to produce some output) on the system to be identified must be performed. When such trials are costly, this disengagement results in wasted data that is not utilized by the evolutionary process. Here we propose that data from futile interactions should be stored during disengagement and automatically reintroduced later, when the population reengages: we refer to this as the test bank. We demonstrate that the advantage of the test bank is twofold: it allows for the discovery of more accurate models, and it reduces the amount of required training data for both parametric identification – parameterizing inner structure – and symbolic identification – approximating inner structure using symbolic equations – of nonlinear systems.
Coevolution of Fitness Predictors
 IEEE Transactions on Evolutionary Computation
, 2008
"... Abstract—We present an algorithm that coevolves fitness predictors, optimized for the solution population, which reduce fitness evaluation cost and frequency, while maintaining evolutionary progress. Fitness predictors differ from fitness models in that they may or may not represent the objective fi ..."
Abstract

Cited by 13 (8 self)
 Add to MetaCart
Abstract—We present an algorithm that coevolves fitness predictors, optimized for the solution population, which reduce fitness evaluation cost and frequency, while maintaining evolutionary progress. Fitness predictors differ from fitness models in that they may or may not represent the objective fitness, opening opportunities to adapt selection pressures and diversify solutions. The use of coevolution addresses three fundamental challenges faced in past fitness approximation research: 1) the model learning investment; 2) the level of approximation of the model; and 3) the loss of accuracy. We discuss applications of this approach and demonstrate its impact on the symbolic regression problem. We show that coevolved predictors scale favorably with problem complexity on a series of randomly generated test problems. Finally, we present additional empirical results that demonstrate that fitness prediction can also reduce solution bloat and find solutions more reliably. Index Terms—Bloat Reduction, coevolution, fitness modeling, symbolic regression.
Coevolving Programs and Unit Tests from their Specification
 In Proceedings of the twentysecond IEEE/ACM International Conference on Automated Software Engineering (ASE ’07
"... Writing a formal specification before implementing a program helps to find problems with the system requirements. The requirements might be for example incomplete and ambiguous. Fixing these types of errors is very difficult and expensive during the implementation phase of the software development c ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
Writing a formal specification before implementing a program helps to find problems with the system requirements. The requirements might be for example incomplete and ambiguous. Fixing these types of errors is very difficult and expensive during the implementation phase of the software development cycle. Although writing a formal specification is usually easier than implementing the actual code, writing a specification requires time, and often it is preferred, instead, to use this time on the implementation. In this paper we introduce for the first time a framework that might evolve any possible generic program from its specification. We use the Genetic Programming to evolve the programs, and at the same time we exploit the specifications to coevolve sets of unit tests. Programs are rewarded on how many tests they do not fail, whereas the unit tests are rewarded on how many programs they make fail. We present and analyse four different problems on which this novel technique is successfully applied.
Measuring Generalization Performance in Coevolutionary Learning
"... Coevolutionary learning involves a training process where training samples are instances of solutions that interact strategically to guide the evolutionary (learning) process. One main research issue is with the generalization performance, i.e., the search for solutions (e.g., inputoutput mappings ..."
Abstract

Cited by 9 (5 self)
 Add to MetaCart
Coevolutionary learning involves a training process where training samples are instances of solutions that interact strategically to guide the evolutionary (learning) process. One main research issue is with the generalization performance, i.e., the search for solutions (e.g., inputoutput mappings) that best predict the required output for any new input that has not been seen during the evolutionary process. However, there is currently no such framework for determining the generalization performance in coevolutionary learning even though the notion of generalization is wellunderstood in machine learning. In this paper, we introduce a theoretical framework to address this research issue. We present the framework in terms of gameplaying although our results are more general. Here, a strategy’s generalization performance is its average performance against all test strategies. Given that the true value may not be determined by solving analytically a closedform formula and is computationally prohibitive, we propose an estimation procedure that computes the average performance against a small sample of random test strategies instead. We perform a mathematical analysis to provide a statistical claim on the accuracy of our estimation procedure, which can be further improved by performing a second estimation on the variance of the random variable. For gameplaying, it is wellknown that one is more interested in the generalization
Coevolution of neural networks using a layered pareto archive
 In Proceedings of the Genetic and Evolutionary Computation Conference
, 2006
"... The Layered Pareto Coevolution Archive (LAPCA) was recently proposed as an effective Coevolutionary Memory (CM) which, under certain assumptions, approximates monotonic progress in coevolution. In this paper, a technique is developed that interfaces the LAPCA algorithm with NeuroEvolution of Augment ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
The Layered Pareto Coevolution Archive (LAPCA) was recently proposed as an effective Coevolutionary Memory (CM) which, under certain assumptions, approximates monotonic progress in coevolution. In this paper, a technique is developed that interfaces the LAPCA algorithm with NeuroEvolution of Augmenting Topologies (NEAT), a method to evolve neural networks with demonstrated efficiency in game playing domains. In addition, the behavior of LAPCA is analyzed for the first time in a complex gameplaying domain: evolving neural network controllers for the game Pong. The technique is shown to keep the total number of evaluations in the order of those required by NEAT, making it applicable to complex domains. Pong players evolved with a LAPCA and with the Hall of Fame (HOF) perform equally well, but the LAPCA is shown to require significantly less space than the HOF. Therefore, combining NEAT and LAPCA is found to be an effective approach to coevolution.
The Nstrikesout algorithm: A steadystate algorithm for coevolution
 In G. Yen (Ed.), Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2006). Piscataway
, 2006
"... Abstract — We introduce the Nstrikesout algorithm, a simple steadystate genetic algorithm for competitive coevolution. The algorithm can be summarised as follows: Run competitions between randomly chosen individuals, keep track of the number of defeats for each individual, and remove any individu ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
Abstract — We introduce the Nstrikesout algorithm, a simple steadystate genetic algorithm for competitive coevolution. The algorithm can be summarised as follows: Run competitions between randomly chosen individuals, keep track of the number of defeats for each individual, and remove any individual which has been defeated N times. Naive application of the algorithm in 2population problems leads to severe disengagement. We find that disengagement can be eliminated (for all tasks involving realvalued continuous scores) by determining ‘victories ’ and ‘defeats ’ between fellow members of the same species, using competitions against a single member of the opposing species as a point of comparison. We apply our algorithm to the “boxgrabbing” problem for artificial 3D creatures introduced by Sims. We compare our algorithm with Sims ’ original Last Elite Opponent algorithm, and describe (and explain) different
Evolutionary multiagent systems
 In Proceedings of the 8th International Conference on Parallel Problem Solving from Nature PPSN04
, 2004
"... Abstract. In MultiAgent learning, agents must learn to select actions that maximize their utility given the action choices of the other agents. Cooperative Coevolution offers a way to evolve multiple elements that together form a whole, by using a separate population for each element. We apply this ..."
Abstract

Cited by 8 (0 self)
 Add to MetaCart
Abstract. In MultiAgent learning, agents must learn to select actions that maximize their utility given the action choices of the other agents. Cooperative Coevolution offers a way to evolve multiple elements that together form a whole, by using a separate population for each element. We apply this setup to the problem of multiagent learning, arriving at an evolutionary multiagent system (EAMAS). We study a problem that requires agents to select their actions in parallel, and investigate the problem solving capacity of the EAMAS for a wide range of settings. Secondly, we investigate the transfer of the COllective INtelligence (COIN) framework to the EAMAS. COIN is a proved engineering approach for learning of cooperative tasks in MASs, and consists of reengineering the utilities of the agents so as to contribute to the global utility. It is found that, as in the Reinforcement Learning case, the use of the Wonderful Life Utility specified by COIN also leads to improved results for the EAMAS. 1
Predatorprey model for discrete sensor placement
 In 8th Annual Symposium on Water Distribution Systems Analysis
, 2006
"... A metaheuristic approach is proposed to design the optimal placement of monitoring stations, for aiming an early detection of the intentional water distribution networks contamination. The approach is based on the use of a predatorprey model, that is applied to multiobjective optimization. The pro ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
A metaheuristic approach is proposed to design the optimal placement of monitoring stations, for aiming an early detection of the intentional water distribution networks contamination. The approach is based on the use of a predatorprey model, that is applied to multiobjective optimization. The proposed algorithm is used to solve the sensor constrained contamination detection problem, which is polynomially equivalent to the asymmetric kcenter problem, so it is NPHard In particular the predatorprey model is applied to find the optimal sensors placement evaluated, according to the four design objectives which are described in the Battle of Water Sensor Networks (BWSN) manifesto. Both predators and preys are subjected to an evolution process. The competing coevolution approach has been chosen to avoid the problem of designing the fitness function or, in other words, to avoid the problem of locating the most representative contamination events. The candidate solutions and tests, which are used to evaluate these solutions, evolve simultaneously to find the optimal evaluation set, and as a consequence to minimize the number of needed checks, during the selection of the optimal solution.