Resolving the Exploration-Exploitation Dilemma in Evolutionary Algorithms: A Novel Human-Centered Framework

• URL: http://arxiv.org/abs/2501.02153v2
• Date: Tue, 01 Apr 2025 23:55:35 GMT
• Title: Resolving the Exploration-Exploitation Dilemma in Evolutionary Algorithms: A Novel Human-Centered Framework
• Authors: Ehsan Shams,
• Abstract summary: A systematic resolution to the exploration-exploitation dilemma in algorithm design requires an independent yet coordinated control over exploration and exploitation.<n>We propose a Human-Centered Two-Phase Search (HCTPS) framework, in which the actualization of (1) and (2) is enabled through an external variable--the Search Space Control.<n>We prove that the HCTPS strictly surpasses the current approach in terms of search space coverage without disrupting the EAs' inherent convergence mechanisms.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evolutionary Algorithms (EAs) are widely employed tools for complex search and optimization tasks; however, the absence of an overarching operational framework that permits a systematic regulation of the exploration-exploitation tradeoff--critical for efficient convergence--restricts the full actualization of their potential, leading to the so-called exploration-exploitation dilemma in algorithm design. A systematic resolution to this dilemma requires: (1) an independent yet coordinated control over exploration and exploitation, and (2) an explicit, computationally feasible, adaptive regulation mechanism. The current, almost decentralized, traditional parameter tuning-centeric approach--lacks the foundation to satisfy these requirements under encoding-imposed structural constraints. We propose a Human-Centered Two-Phase Search (HCTPS) framework, in which the actualization of (1) and (2) is enabled through an external configuration variable--the Search Space Control Parameter (SSCP). As the sole control knob of HCTPS, the SSCP centralizes exploration adjustments, sparing users from micromanaging traditional parameters with unintelligible interdependencies. To this construct, the human user serves as a meta-parameter, adaptively steering the regulatory process via SSCP adjustments. We prove that the HCTPS strictly surpasses the current approach in terms of search space coverage without disrupting the EAs' inherent convergence mechanisms, demonstrate a concrete instantiation of it--using the Genetic Algorithm as the underlying heuristic on a suite of global benchmark unconstrained optimization problems, provide a through assessment of the proposed framework, and envision future research directions. Any search algorithm prone to this dilemma can be applied in light of the proposed framework, being algorithm-agnostic by design.

Related papers

• Tuning-Free Structured Sparse PCA via Deep Unfolding Networks [5.931547772157972]
  We propose a new type of sparse principal component analysis (PCA) for unsupervised feature selection (UFS) We use an interpretable deep unfolding network that translates iterative optimization steps into trainable neural architectures. This innovation enables automatic learning of the regularization parameters, effectively bypassing the empirical tuning requirements of conventional methods.
  arXiv  Detail & Related papers  (2025-02-28T08:32:51Z)
• Learning-Based Design of LQG Controllers in Quantum Coherent Feedback [11.494992140467984]
  We propose a differential evolution algorithm specifically tailored for the design of Linear-Quadratic-Gaussian (LQG) controllers in quantum systems. The algorithm incorporates specialized modules, including relaxed feasibility rules, a scheduled penalty function, adaptive search range adjustment, and the bet-and-run'' strategy. The proposed approach holds significant potential for application to other linear quantum systems in performance optimization tasks subject to physically feasible constraints.
  arXiv  Detail & Related papers  (2025-02-12T07:24:22Z)
• Optimal Control Operator Perspective and a Neural Adaptive Spectral Method [43.684201849848314]
  Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. We propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach.
  arXiv  Detail & Related papers  (2024-12-17T02:06:34Z)
• Deep Reinforcement Learning for Online Optimal Execution Strategies [49.1574468325115]
  This paper tackles the challenge of learning non-Markovian optimal execution strategies in dynamic financial markets. We introduce a novel actor-critic algorithm based on Deep Deterministic Policy Gradient (DDPG) We show that our algorithm successfully approximates the optimal execution strategy.
  arXiv  Detail & Related papers  (2024-10-17T12:38:08Z)
• An Improved Artificial Fish Swarm Algorithm for Solving the Problem of Investigation Path Planning [8.725702964289479]
  We propose a chaotic artificial fish swarm algorithm based on multiple population differential evolution (DE-CAFSA) We incorporate adaptive field of view and step size adjustments, replace random behavior with the 2-opt operation, and introduce chaos theory and sub-optimal solutions. Experimental results demonstrate that DE-CAFSA outperforms other algorithms on various public datasets of different sizes.
  arXiv  Detail & Related papers  (2023-10-20T09:35:51Z)
• Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design [54.39859618450935]
  We show that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL tasks. Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-supervised-training distribution impact the performance of these algorithms.
  arXiv  Detail & Related papers  (2023-10-04T12:52:56Z)
• PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement [59.6260680005195]
  We present a novel Person Search framework based on the Diffusion model, PSDiff.<n> PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths.<n>Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way.
  arXiv  Detail & Related papers  (2023-09-20T08:16:39Z)
• Efficient Model-Free Exploration in Low-Rank MDPs [76.87340323826945]
  Low-Rank Markov Decision Processes offer a simple, yet expressive framework for RL with function approximation. Existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions. We propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs.
  arXiv  Detail & Related papers  (2023-07-08T15:41:48Z)
• Neural Algorithmic Reasoning Without Intermediate Supervision [21.852775399735005]
  We focus on learning neural algorithmic reasoning only from the input-output pairs without appealing to the intermediate supervision. We build a self-supervised objective that can regularise intermediate computations of the model without access to the algorithm trajectory. We demonstrate that our approach is competitive to its trajectory-supervised counterpart on tasks from the CLRSic Algorithmic Reasoning Benchmark.
  arXiv  Detail & Related papers  (2023-06-23T09:57:44Z)
• Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI [108.08079323459822]
  This paper studies a new multi-intelligent edge artificial-latency (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) We measure the inference accuracy by adopting an approximate but tractable metric, namely discriminant gain.
  arXiv  Detail & Related papers  (2022-07-03T06:57:07Z)
• VNE Strategy based on Chaotic Hybrid Flower Pollination Algorithm Considering Multi-criteria Decision Making [12.361459296815559]
  Design strategy of hybrid flower pollination algorithm for Virtual Network Embedding (VNE) problem is discussed. Cross operation is used to replace the cross-pollination operation to complete the global search. Life cycle mechanism is introduced as a complement to the traditional fitness-based selection strategy.
  arXiv  Detail & Related papers  (2022-02-07T00:57:00Z)
• DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization [43.31016937305845]
  Internet-of-things, networked sensing, autonomous systems and federated learning call for decentralized algorithms for finite-sum optimizations. We develop DEcentralized STochastic REcurSive methodDESTRESS for non finite-sum optimization. Detailed theoretical and numerical comparisons show that DESTRESS improves upon prior decentralized algorithms.
  arXiv  Detail & Related papers  (2021-10-04T03:17:41Z)
• An Overview and Experimental Study of Learning-based Optimization Algorithms for Vehicle Routing Problem [49.04543375851723]
  Vehicle routing problem (VRP) is a typical discrete optimization problem. Many studies consider learning-based optimization algorithms to solve VRP. This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.
  arXiv  Detail & Related papers  (2021-07-15T02:13:03Z)
• Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT [106.83952081124195]
  Reinforcement learning (RL) has been widely investigated and shown to be a promising solution for decision-making and optimal control processes. We propose an adaptive ADMM (asI-ADMM) algorithm and apply it to decentralized RL with edge-computing-empowered IIoT networks. Experiment results show that our proposed algorithms outperform the state of the art in terms of communication costs and scalability, and can well adapt to complex IoT environments.
  arXiv  Detail & Related papers  (2021-06-30T16:49:07Z)
• A Meta-Heuristic Search Algorithm based on Infrasonic Mating Displays in Peafowls [0.0]
  Simplistic methods such as exhaustive search become computationally expensive and unreliable as the solution space for search algorithms increase. This research proposes an Infrasonic Search Algorithm, inspired from the Gravitational Search Algorithm and the mating behaviour in peafowls.
  arXiv  Detail & Related papers  (2021-06-28T09:04:51Z)
• AutoSpace: Neural Architecture Search with Less Human Interference [84.42680793945007]
  Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. We propose a novel differentiable evolutionary framework named AutoSpace, which evolves the search space to an optimal one. With the learned search space, the performance of recent NAS algorithms can be improved significantly compared with using previously manually designed spaces.
  arXiv  Detail & Related papers  (2021-03-22T13:28:56Z)
• Multi-Level Evolution Strategies for High-Resolution Black-Box Control [0.2320417845168326]
  This paper introduces a multi-level (m-lev) mechanism into Evolution Strategies (ESs) It addresses a class of global optimization problems that could benefit from fine discretization of their decision variables.
  arXiv  Detail & Related papers  (2020-10-04T09:24:40Z)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)
• Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization [64.26238893241322]
  Simple algorithms have been shown to lead to good empirical results in many contexts. Several works have pursued rigorous analytical justification for studying non optimization problems. A key insight in these analyses is that perturbations play a critical role in allowing local descent algorithms.
  arXiv  Detail & Related papers  (2020-03-31T16:54:22Z)
• Decentralized MCTS via Learned Teammate Models [89.24858306636816]
  We present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search. We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators.
  arXiv  Detail & Related papers  (2020-03-19T13:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.