Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity

• URL: http://arxiv.org/abs/2504.01915v2
• Date: Fri, 04 Apr 2025 15:03:56 GMT
• Title: Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity
• Authors: Lisa Coiffard, Paul Templier, Antoine Cully,
• Abstract summary: Policy optimization seeks the best solution to a control problem according to an objective or fitness function.<n>In this paper, we show that unsupervised QD algorithms efficiently solve deceptive optimization problems without domain expertise.
• Score: 4.787389127632926
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Policy optimization seeks the best solution to a control problem according to an objective or fitness function, serving as a fundamental field of engineering and research with applications in robotics. Traditional optimization methods like reinforcement learning and evolutionary algorithms struggle with deceptive fitness landscapes, where following immediate improvements leads to suboptimal solutions. Quality-diversity (QD) algorithms offer a promising approach by maintaining diverse intermediate solutions as stepping stones for escaping local optima. However, QD algorithms require domain expertise to define hand-crafted features, limiting their applicability where characterizing solution diversity remains unclear. In this paper, we show that unsupervised QD algorithms - specifically the AURORA framework, which learns features from sensory data - efficiently solve deceptive optimization problems without domain expertise. By enhancing AURORA with contrastive learning and periodic extinction events, we propose AURORA-XCon, which outperforms all traditional optimization baselines and matches, in some cases even improving by up to 34%, the best QD baseline with domain-specific hand-crafted features. This work establishes a novel application of unsupervised QD algorithms, shifting their focus from discovering novel solutions toward traditional optimization and expanding their potential to domains where defining feature spaces poses challenges.

Related papers

• Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization [0.0]
  We introduce Vector Quantized-Elites (VQ-Elites), a novel Quality-Diversity algorithm that autonomously constructs a structured behavioral space grid. At the core of VQ-Elites is the integration of Vector Quantized Variational Autoencoders, which enables the dynamic learning of behavioral descriptors. We validate VQ-Elites on robotic arm pose-reaching and mobile robot space-covering tasks.
  arXiv  Detail & Related papers  (2025-04-10T18:23:19Z)
• Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement Learning [29.551883712536295]
  Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution.<n>We propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy.
  arXiv  Detail & Related papers  (2025-01-01T16:08:40Z)
• Learning Joint Models of Prediction and Optimization [56.04498536842065]
  Predict-Then-Then framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models.
  arXiv  Detail & Related papers  (2024-09-07T19:52:14Z)
• Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach [51.63921041249406]
  Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. A novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication.
  arXiv  Detail & Related papers  (2024-06-19T07:17:04Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Quantum Inspired Chaotic Salp Swarm Optimization for Dynamic Optimization [4.44483539967295]
  We study a variant of SSA known as QSSO, which integrates the principles of quantum computing. A chaotic operator is employed with quantum computing to respond to change and guarantee to increase individual searchability. As promised, the introduced QCSSO is discovered as the rival algorithm for DOPs.
  arXiv  Detail & Related papers  (2024-01-21T02:59:37Z)
• Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains [2.639902239625779]
  We introduce Archive Reproducibility Improvement Algorithm (ARIA) ARIA is a plug-and-play approach that improves the quality of solutions present in an archive. We show that our algorithm enhances the quality and descriptor space coverage of any given archive by at least 50%.
  arXiv  Detail & Related papers  (2023-04-07T14:45:14Z)
• ARES: An Efficient Algorithm with Recurrent Evaluation and Sampling-Driven Inference for Maximum Independent Set [48.57120672468062]
  This paper introduces an efficient algorithm for the Maximum Independent Set (MIS) problem, incorporating two innovative techniques. The proposed algorithm outperforms state-of-the-art algorithms in terms of solution quality, computational efficiency, and stability.
  arXiv  Detail & Related papers  (2022-08-16T14:39:38Z)
• An Effective and Efficient Evolutionary Algorithm for Many-Objective Optimization [2.5594423685710814]
  We develop an effective evolutionary algorithm (E3A) that can handle various many-objective problems. In E3A, inspired by SDE, a novel population maintenance method is proposed. We conduct extensive experiments and show that E3A performs better than 11 state-of-the-art many-objective evolutionary algorithms.
  arXiv  Detail & Related papers  (2022-05-31T15:35:46Z)
• Few-shot Quality-Diversity Optimization [50.337225556491774]
  Quality-Diversity (QD) optimization has been shown to be effective tools in dealing with deceptive minima and sparse rewards in Reinforcement Learning. We show that, given examples from a task distribution, information about the paths taken by optimization in parameter space can be leveraged to build a prior population, which when used to initialize QD methods in unseen environments, allows for few-shot adaptation. Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.
  arXiv  Detail & Related papers  (2021-09-14T17:12:20Z)
• BOP-Elites, a Bayesian Optimisation algorithm for Quality-Diversity search [0.0]
  We propose the Bayesian optimisation of Elites (BOP-Elites) algorithm. By considering user defined regions of the feature space as 'niches' our task is to find the optimal solution in each niche. The resulting algorithm is very effective in identifying the parts of the search space that belong to a niche in feature space, and finding the optimal solution in each niche.
  arXiv  Detail & Related papers  (2020-05-08T23:49:13Z)
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning [96.01176486957226]
  Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems.
  arXiv  Detail & Related papers  (2020-01-03T11:01:52Z)

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.