A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning

E Brochu, VM Cora, N De Freitas - ar** strategies
Z Yin, Z Yang, M Van De Panne, KK Yin - ACM Transactions on Graphics …, 2021 - dl.acm.org
We present a framework that enables the discovery of diverse and natural-looking motion
strategies for athletic skills such as the high jump. The strategies are realized as control …

Ordered preference elicitation strategies for supporting multi-objective decision making

LM Zintgraf, DM Roijers, S Linders, CM Jonker… - ar** styles
Z Yang, K Yin, L Liu - ACM Transactions on Graphics (TOG), 2022 - dl.acm.org
Learning dexterous manipulation skills is a long-standing challenge in computer graphics
and robotics, especially when the task involves complex and delicate interactions between …

Efficient hyperparameter optimization for physics-based character animation

Z Yang, Z Yin - Proceedings of the ACM on Computer Graphics and …, 2021 - dl.acm.org
Physics-based character animation has seen significant advances in recent years with the
adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods …

Interactive Bayesian optimization: learning user preferences for graphics and animation

E Brochu - 2010 - open.library.ubc.ca
Bayesian optimization with Gaussian processes has become increasingly popular in the
machine learning community. It is efficient and can be used when very little is known about …

The human in the infinite loop: A case study on revealing and explaining human-AI interaction loop failures

C Ou, D Buschek, S Mayer, A Butz - Proceedings of Mensch Und …, 2022 - dl.acm.org
Interactive AI systems increasingly employ a human-in-the-loop strategy. This creates new
challenges for the HCI community when designing such systems. We reveal and investigate …

[PDF][PDF] Thesis Supervisor: Takeo Igarashi 五十嵐 健夫

Y Koyama - 2016 - repository.dl.itc.u-tokyo.ac.jp
Tweaking parameter settings is one of the most fundamental tasks in many design domains,
including 2-dimensional graphic design and 3-dimensional product design. The purpose of …

[CITAT][C] Motor control and strategy discovery for physically simulated characters

Z Yin - 2021 - Simon Fraser University