paper-with-me

Papers

Efficient Quality-Diversity Optimization through Diverse Quality Species

2023-04-14 · Ryan Wickman, Bibek Poudel, Michael Villarreal, Xiaofei Zhang, Weizi Li

A prevalent limitation of optimizing over a single objective is that it can be misguided, becoming trapped in local optimum. This can be rectified by Quality-Diversity (QD) algorithms, where a population of high-quality and diverse solutions to a problem is preferred. Most conventional QD approaches, for example, MAP-Elites, explicitly manage a behavioral archive where solutions are broken down into predefined niches. In this work, we show that a diverse population of solutions can be found without the limitation of needing an archive or defining the range of behaviors in advance. Instead, we break down solutions into independently evolving species and use unsupervised skill discovery to learn diverse, high-performing solutions. We show that this can be done through gradient-based mutations that take on an information theoretic perspective of jointly maximizing mutual information and performance. We propose Diverse Quality Species (DQS) as an alternative to archive-based QD algorithms. We evaluate it over several simulated robotic environments and show that it can learn a diverse set of solutions from varying species. Furthermore, our results show that DQS is more sample-efficient and performant when compared to other QD algorithms. Relevant code and hyper-parameters are available at: https://github.com/rwickman/NEAT_RL.

📄 PDF Abstract BibTeX arXiv:2304.07425

Code (1)

rwickman/neat_rl 공식 구현 pytorch

Tasks

Diversity

Similar Papers 제목 키워드 기반

An Analysis of Phenotypic Diversity in Multi-Solution Optimization

2021-05-10 · Alexander Hagg, Mike Preuss, Alexander Asteroth, Thomas Bäck

More and more, optimization methods are used to find diverse solution sets. We compare solution diversity in multi-objective optimization, multimodal optimization, and quality diversity in a simple domain. We show that m…

DiversityMultiobjective Optimization

Diverse Preference Optimization

2025-01-30 · Jack Lanchantin, Angelica Chen, Shehzaad Dhuliawala, Ping Yu 외

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated respon…

Diversity

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

2023-10-18 · Li Ding, Jenny Zhang, Jeff Clune, Lee Spector 외

Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for av…

DiversityImage Generationreinforcement-learningReinforcement Learning+4

Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimization

2023-03-28 · Alexander Hagg, Martin L. Kliemank, Alexander Asteroth, Dominik Wilde 외

Quality diversity algorithms can be used to efficiently create a diverse set of solutions to inform engineers' intuition. But quality diversity is not efficient in very expensive problems, needing 100.000s of evaluations…

Diversity

Evolutionary Multi-Objective Diversity Optimization

2024-01-15 · Anh Viet Do, Mingyu Guo, Aneta Neumann, Frank Neumann

Creating diverse sets of high quality solutions has become an important problem in recent years. Previous works on diverse solutions problems consider solutions' objective quality and diversity where one is regarded as t…

Diversity