Recently, Meta-Black-Box-Optimization (MetaBBO) methods significantly enhance the performance of traditional black-box optimizers through meta-learning flexible and generalizable meta-level policies that excel in dynamic algorithm configuration (DAC) tasks within the low-level optimization, reducing the expertise required to adapt optimizers for novel optimization tasks. Though promising, existing MetaBBO methods heavily rely on human-crafted feature extraction approach to secure learning effectiveness. To address this issue, this paper introduces a novel MetaBBO method that supports automated feature learning during the meta-learning process, termed as RLDE-AFL, which integrates a learnable feature extraction module into a reinforcement learning-based DE method to learn both the feature encoding and meta-level policy. Specifically, we design an attention-based neural network with mantissa-exponent based embedding to transform the solution populations and corresponding objective values during the low-level optimization into expressive landscape features. We further incorporate a comprehensive algorithm configuration space including diverse DE operators into a reinforcement learning-aided DAC paradigm to unleash the behavior diversity and performance of the proposed RLDE-AFL. Extensive benchmark results show that co-training the proposed feature learning module and DAC policy contributes to the superior optimization performance of RLDE-AFL to several advanced DE methods and recent MetaBBO baselines over both synthetic and realistic BBO scenarios.

Meta-Black-Box Optimization (MetaBBO) streamlines the automation of optimization algorithm design through meta-learning. It typically employs a bi-level structure: the meta-level policy undergoes meta-training to reduce the manual effort required in developing algorithms for low-level optimization tasks. The original MetaBox (2023) provided the first open-source framework for reinforcement learning-based single-objective MetaBBO. However, its relatively narrow scope no longer keep pace with the swift advancement in this field. In this paper, we introduce MetaBox-v2 (\url{https://github.com/MetaEvo/MetaBox}) as a milestone upgrade with four novel features: 1) a unified architecture supporting RL, evolutionary, and gradient-based approaches, by which we reproduce $23$ up-to-date baselines; 2) efficient parallelization schemes, which reduce the training/testing time by $10-40$x; 3) a comprehensive benchmark suite of $18$ synthetic/realistic tasks ($1900$+ instances) spanning single-objective, multi-objective, multi-model, and multi-task optimization scenarios; 4) plentiful and extensible interfaces for custom analysis/visualization and integrating to external optimization tools/benchmarks. To show the utility of MetaBox-v2, we carry out a systematic case study that evaluates the built-in baselines in terms of the optimization performance, generalization ability and learning efficiency. Valuable insights are concluded from thorough and detailed analysis for practitioners and those new to the field.

The analysis of complex scattering patterns in SAR images of high-voltage power lines is important to comprehend the multireflection effects of these cylindrical shape structures. Such insights are invaluable for applications related to inspection management, particularly in safety analysis and ongoing monitoring. This letter introduces a novel point scattering tracing method to dissect the intricate multireflection effects of power lines in high-resolution X-band SAR data. The paths of multireflection events at the power lines are delineated through a proposed model, which leverages LiDAR point cloud data and SAR system parameters with subpixel precision. Under the condition of a parallel tangent line to the azimuth direction, the proposed quadratic polynomial model is solvable to pinpoint the centers of the single- and triple-reflection point signatures of power lines in SAR coordinate. The analysis of time-series SAR images reveals the activation of the double- and triple-reflection effects induced by water ripples or swinging lines, which is challenging to quantify. The proposed mathematical model is validated through testing with TerraSAR-X (TSX) data in two distinct cases, and the results are highly consistent. The new insights of both visible and invisible components of the double and triple reflections of power lines introduce new challenges to SAR research.