# Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs

arXiv: https://arxiv.org/abs/2008.07119 · HTML: https://mlsanity.com/paper/2008.07119/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 19 of 19)

- [Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications](https://mlsanity.com/paper/2211.08064/) (2022)
- [CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis](https://mlsanity.com/paper/2103.06242/) (2021)
- [Topology Optimization via Machine Learning and Deep Learning: A Review](https://mlsanity.com/paper/2210.10782/) (2022)
- [Deep Learning in Deterministic Computational Mechanics](https://mlsanity.com/paper/2309.15421/) (2023)
- [Geometry-Informed Neural Networks](https://mlsanity.com/paper/2402.14009/) (2024)
- [Deep Learning-Based Inverse Design for Engineering Systems: Multidisciplinary Design Optimization of Automotive Brakes](https://mlsanity.com/paper/2202.13309/) (2022)
- [Wheel Impact Test by Deep Learning: Prediction of Location and Magnitude of Maximum Stress](https://mlsanity.com/paper/2210.01126/) (2022)
- [Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges](https://mlsanity.com/paper/2211.16406/) (2022)
- [Dynamically configured physics-informed neural network in topology optimization applications](https://mlsanity.com/paper/2312.06993/) (2023)
- [DeepWheel: Generating a 3D Synthetic Wheel Dataset for Design and Performance Evaluation](https://mlsanity.com/paper/2504.11347/) (2025)
- [A surrogate model for topology optimisation of elastic structures via parametric autoencoders](https://mlsanity.com/paper/2507.22539/) (2025)
- [Inverse design with conditional cascaded diffusion models](https://mlsanity.com/paper/2408.08526/) (2024)
- [Three-dimensional Deep Shape Optimization with a Limited Dataset](https://mlsanity.com/paper/2506.12326/) (2025)
- [A Generative Neural Network Approach for 3D Multi-Criteria Design Generation and Optimization of an Engine Mount for an Unmanned Air Vehicle](https://mlsanity.com/paper/2311.03414/) (2023)
- [Trajectory-Aware Flow Matching for Topology Optimisation](https://mlsanity.com/paper/2607.14652/) (2026)
- [Deep Concept Identification for Generative Design](https://mlsanity.com/paper/2410.20061/) (2024)
- [AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control](https://mlsanity.com/paper/2603.27000/) (2026)
- [Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework](https://mlsanity.com/paper/2606.21378/) (2026)
- [Generalized Kalman filter based temporal difference reinforcement learning](https://mlsanity.com/paper/2607.20010/) (2026)

## Abstract (arXiv)

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse topology designs, which cannot be represented by conventional parametric design approaches. Recently, data-driven topology optimization research has started to exploit artificial intelligence, such as deep learning or machine learning, to improve the capability of design exploration. This study proposes a reinforcement learning (RL) based generative design process, with reward functions maximizing the diversity of topology designs. We formulate generative design as a sequential problem of finding optimal design parameter combinations in accordance with a given reference design. Proximal Policy Optimization is used as the learning framework, which is demonstrated in the case study of an automotive wheel design problem. To reduce the heavy computational burden of the wheel topology optimization process required by our RL formulation, we approximate the optimization process with neural networks. With efficient data preprocessing/augmentation and neural architecture, the neural networks achieve a generalized performance and symmetricity-reserving characteristics. We show that RL-based generative design produces a large number of diverse designs within a short inference time by exploiting GPU in a fully automated manner. It is different from the previous approach using CPU which takes much more processing time and involving human intervention.