{"repo":"Pascal-Jansen/Bayesian-Optimization-for-Unity","free":true,"listed":false,"github":"https://github.com/Pascal-Jansen/Bayesian-Optimization-for-Unity","clone":"git clone https://github.com/Pascal-Jansen/Bayesian-Optimization-for-Unity.git","description":"A lightweight Unity asset for running powerful Bayesian optimization. It supports practical human-in-the-loop workflows where the optimizer proposes parameter values, collects user feedback as objective scores, updates the model, and recommends the next design iteration.","language":"C#","stars":40,"topics":["bayesian-optimization","botorch","human-in-the-loop","multi-objective-optimization","unity"],"license":"MIT","category":"game-templates","readme_excerpt":"Bayesian Optimization for Unity Pascal Jansen , Ulm University Mark Colley , University College London About This Unity asset provides an end-to-end, Human-in-the-Loop (HITL) Bayesian Optimization workflow (single- and multi-objective) built on botorch.org. It lets you declare design parameters and objectives in Unity, runs a Python backend, and loops with users inside your Unity scene. The result is an efficient search over large design spaces, yielding trade-off designs on the Pareto front . Why this matters. Users typically have diverse preferences, needs, and abilities. Thus, manual design parameter tuning is often slow and potentially biased; A/B and grid search scale poorly. Instead, MOBO uses probabilistic surrogate models and principled acquisition to balance design exploration and exploitation, reducing the number of user trials required to achieve a high-quality design for individuals. Key Features - Configure design parameters, objectives, and optimizer hyperparameters directly in Unity. - Automatic, robust communication with a BoTorch-based MOBO process. - MOBO metric calculations use moocore for Pareto-front and hypervolume utilities. - Cost-aware BO backend (CABOP) for cases where design evaluations have different costs, with single-objective and scalarized multi-objective modes; see Langerak et al.'s Cost-Aware Bayesian Optimization for Prototyping Interactive Devices for background. - Dynamic BO backend (DBO) for single-objective studies whose cost drifts duri","default_branch":null,"files":null,"tree":[],"storefront":"/r/Pascal-Jansen","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Pascal-Jansen/Bayesian-Optimization-for-Unity/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}