Resolving the Exploration-Exploitation Dilemma in Evolutionary Algorithms: A Novel Human-Centered Framework
Ehsan Shams
TL;DR
This work addresses the exploration-exploitation dilemma in Evolutionary Algorithms by introducing a human-centered, two-phase framework (HCTPS) that externalizes exploration through a single control knob, the Search Space Size Control Parameter (SSCP). The human acts as a meta-parameter to adaptively steer exploration across a global phase and a sequence of localized sub-cubes in a subsequent local phase, while preserving the EA’s intrinsic exploitation dynamics. The authors prove a theoretical guarantee that HCTPS expands search coverage beyond traditional approaches and demonstrate a GA-based instantiation (HCTPS-GA) that achieves superior performance on a suite of 30-dimensional global unconstrained benchmarks, under a fixed evaluation budget. The framework is algorithm-agnostic, computationally feasible, and offers interpretable, parallelizable exploration strategies, with significant implications for improving the robustness and reach of global optimization in complex landscapes.
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.