Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference最新文献_第2页

Stable and Sample-Efficient Policy Search for Continuous Control via Hybridizing Phenotypic Evolutionary Algorithm with the Double Actors Regularized Critics 基于双角色正则化批评的杂交表型进化算法的连续控制稳定高效策略搜索

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590455

Thai Huy Nguyen, N. H. Luong

{"title":"Stable and Sample-Efficient Policy Search for Continuous Control via Hybridizing Phenotypic Evolutionary Algorithm with the Double Actors Regularized Critics","authors":"Thai Huy Nguyen, N. H. Luong","doi":"10.1145/3583131.3590455","DOIUrl":"https://doi.org/10.1145/3583131.3590455","url":null,"abstract":"Evolutionary Reinforcement Learning arises from hybridizing the sample efficiency of policy gradient with the stability of evolutionary computation. Proximal Distilled Evolutionary Reinforcement Learning (PDERL) implements the hybridization by having information transferred between an RL agent operating alongside a population of candidate policies. PDERL employs two phenotype-based variation operators, behavior distillation crossover and proximal mutation, which exhibit better effectiveness compared to traditional genotype-based operators. We demonstrate that the proximal mutation is sensitive to its mutation magnitude hyperparameter, which yields damaging effects if its value is improperly set. Inspired from Differential Evolution, we propose a novel mutation procedure that operates on action vectors generated by candidate policies. The phenotypic differential mutation (PhDM) shows its stability in diversity maintenance with little disruption. A recently-introduced actor-critic policy gradient algorithm, Double Actors Regularized Critics (DARC), exhibits a superior sample efficiency. DARC alleviates both overestimation and underestimation bias via the usage of two actors for better exploration and a dedicated critic regularization technique. In this paper, we restructure PDERL to incorporate PhDM and the policy gradient mechanism of DARC. Experimental results show that our Phenotypic Evolutionary DARC (PhEDARC) outperforms both PDERL and DARC in four control tasks from OpenAI Gym. Ablation studies support our design choices.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"70 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77860633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Many-objective (Combinatorial) Optimization is Easy 多目标(组合)优化很容易

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590475

A. Liefooghe, Manuel López-Ibáñez

{"title":"Many-objective (Combinatorial) Optimization is Easy","authors":"A. Liefooghe, Manuel López-Ibáñez","doi":"10.1145/3583131.3590475","DOIUrl":"https://doi.org/10.1145/3583131.3590475","url":null,"abstract":"It is a common held assumption that problems with many objectives are harder to optimize than problems with two or three objectives. In this paper, we challenge this assumption and provide empirical evidence that increasing the number of objectives tends to reduce the difficulty of the landscape being optimized. Of course, increasing the number of objectives brings about other challenges, such as an increase in the computational effort of many operations, or the memory requirements for storing non-dominated solutions. More precisely, we consider a broad range of multi- and many-objective combinatorial benchmark problems, and we measure how the number of objectives impacts the dominance relation among solutions, the connectedness of the Pareto set, and the landscape multimodality in terms of local optimal solutions and sets. Our analysis shows the limit behavior of various landscape features when adding more objectives to a problem. Our conclusions do not contradict previous observations about the inability of Pareto-optimality to drive search, but we explain these observations from a different perspective. Our findings have important implications for the design and analysis of many-objective optimization algorithms.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78787179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Region-based Evaluation Particle Swarm Optimization with Dual Solution Libraries for Real-time Traffic Signal Timing Optimization 基于双解库的区域评价粒子群实时交通信号配时优化

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590350

Chikun Zhang, Jian-Yu Li, Chun-Hua Chen, Yunjie Li, Zhi-hui Zhan

{"title":"Region-based Evaluation Particle Swarm Optimization with Dual Solution Libraries for Real-time Traffic Signal Timing Optimization","authors":"Chikun Zhang, Jian-Yu Li, Chun-Hua Chen, Yunjie Li, Zhi-hui Zhan","doi":"10.1145/3583131.3590350","DOIUrl":"https://doi.org/10.1145/3583131.3590350","url":null,"abstract":"Traffic signal timing optimization (TSTO) is a significant topic in the smart city. However, there are two challenges when solving TSTO. Firstly, it often uses time-consuming simulation software to evaluate candidate solutions, therefore it is an expensive optimization problem. Secondly, as the traffic flow changes rapidly in TSTO, providing a timing scheme to respond to the change immediately is difficult. To address the above challenges, we propose a region-based evaluation particle swarm optimization algorithm (REPSO) with dual solution libraries, which has three novel designs. First, two solution libraries are built for undersaturated and oversaturated traffic flow states, respectively, which can be used to fast provide a signal timing scheme for a traffic flow in real-time. Second, a knowledge-assisted initialization strategy is proposed and adopted to assist the initialization of new solutions based on the knowledge in the two solution libraries. Third, a region-based evaluation strategy is proposed to reduce the number of fitness evaluations, which can also greatly reduce the construction time of the solution libraries. The performance of REPSO is validated by comparing with six signal timing methods in both undersaturated and oversaturated traffic flow states, showing the better general performance of REPSO.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83279923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interactive Latent Diffusion Model 相互作用潜伏扩散模型

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590471

Mathurin Videau, Nickolai Knizev, A. Leite, Marc Schoenauer, Olivier Teytaud

引用次数: 0

Reducing Overparameterization of Symbolic Regression Models with Equality Saturation 具有相等饱和的符号回归模型的过参数化

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590346

F. O. de França, G. Kronberger

引用次数: 0

Adaptive Team Cooperative Co-Evolution for a Multi-Rover Distribution Problem 多漫游车分布问题的自适应团队合作协同进化

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590500

Nicolas Fontbonne, N. Maudet, Nicolas Bredèche

{"title":"Adaptive Team Cooperative Co-Evolution for a Multi-Rover Distribution Problem","authors":"Nicolas Fontbonne, N. Maudet, Nicolas Bredèche","doi":"10.1145/3583131.3590500","DOIUrl":"https://doi.org/10.1145/3583131.3590500","url":null,"abstract":"This paper deals with policy learning for a team of heterogeneous robotic agents when the whole team shares a single reward. We address the problem of providing an accurate estimation of the contribution of each agent in tasks where coordination between agents requires joint policy updates of two (or more) agents. This is typically the case when two agents must simultaneously modify their behaviors to perform a joint action that leads to a performance gain for the whole team. We propose a cooperative co-evolutionary algorithm extended with a multi-armed bandit algorithm that dynamically adjusts the number of agents that should update their policies simultaneously, aiming both for performance and learning speed. We use a realistic robotic multi-rover task where agents must physically distribute themselves on points of interest of different natures to complete the task. Results show that the algorithm is able to select the best group size for policy updates that reflects the task's coordination requirements. Surprisingly, we also reveal that coupling between agents' actions in a realistic setup can also emerge from interactions at the phenotypical level, hinting at subtle interactions during learning between the control parameter space and the behavioral space.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"259 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91325759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cooperative Co-Evolution for Ensembles of Nested Dichotomies for Multi-Class Classification 多类分类中嵌套二分类集合的协同进化

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590457

Marcel Wever, Miran Özdogan, E. Hüllermeier

引用次数: 0

Dynamic Depth for Better Generalization in Continued Fraction Regression 连续分数回归中更好泛化的动态深度

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590461

P. Moscato, A. Ciezak, N. Noman

{"title":"Dynamic Depth for Better Generalization in Continued Fraction Regression","authors":"P. Moscato, A. Ciezak, N. Noman","doi":"10.1145/3583131.3590461","DOIUrl":"https://doi.org/10.1145/3583131.3590461","url":null,"abstract":"A continued fraction expansion represents a real number as an expression obtained by iteratively extracting the largest whole number from its fractional part and inverting the remainder. Continued Fraction Regression (CFR) is a method for approximating unknown target functions from data. The key idea is representing the target function as an analytic continued fraction expansion. This is achieved through an optimization approach, which searches the set of possible fractions to find the best approximating fraction for the given data. This research investigates the relationship between truncated fraction depth, accuracy, complexity, and training time in the CFR method for challenging regression problems. Specifically, low-sample synthetic datasets with Gaussian noise are considered, which we use as a proxy for low-sample dynamical systems with underlying models obscured by measurement errors. We propose and assess the performance of three depth-regulating CFR approaches against six modern symbolic regression methods. We reinforce the strong generalization capacity of the CFR method while reducing model complexity and execution time. Our method achieves the most 1st place rankings in testing against its competitors on 21 Nguyen datasets. It is never worse than 3rd for any dataset while taking at most 4% of the training time of its closest competitor.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78722827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Relieving Genetic Programming from Coefficient Learning for Symbolic Regression via Correlation and Linear Scaling 利用相关和线性标度方法缓解符号回归中系数学习的遗传规划问题

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3595918

Qi Chen, Bing Xue, W. Banzhaf, Mengjie Zhang

{"title":"Relieving Genetic Programming from Coefficient Learning for Symbolic Regression via Correlation and Linear Scaling","authors":"Qi Chen, Bing Xue, W. Banzhaf, Mengjie Zhang","doi":"10.1145/3583131.3595918","DOIUrl":"https://doi.org/10.1145/3583131.3595918","url":null,"abstract":"The difficulty of learning optimal coefficients in regression models using only genetic operators has long been a challenge in genetic programming for symbolic regression. As a simple but effective remedy it has been proposed to perform linear scaling of model outputs prior to a fitness evaluation. Recently, the use of a correlation coefficient-based fitness function with a post-processing linear scaling step for model alignment has been shown to outperform error-based fitness functions in generating symbolic regression models. In this study, we compare the impact of four evaluation strategies on relieving genetic programming (GP) from learning coefficients in symbolic regression and focusing on learning the more crucial model structure. The results from 12 datasets, including ten real-world tasks and two synthetic datasets, confirm that all these strategies assist GP to varying degrees in learning coefficients. Among the them, correlation fitness with one-time linear scaling as post-processing, due to be the most efficient while bringing notable benefits to the performance, is the recommended strategy to relieve GP from learning coefficients.","PeriodicalId":89841,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82329921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving Neighborhood Exploration Mechanism to Speed up PLS 完善邻域探索机制，加快PLS的实现

Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference Pub Date : 2023-07-15 DOI: 10.1145/3583131.3590445

Yuhao Kang, Jialong Shi, Jianyong Sun, Ye Fan

引用次数: 0