Efficient Hyperparameter Optimization for Physics-based Character Animation

Abstract

Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods are usually computationally expensive and their performance crucially depends on the choice of hyperparameters. Tuning hyperparameters for these methods often requires repetitive training of control policies, which is even more computationally prohibitive. In this work, we propose a novel Curriculum-based Multi-Fidelity Bayesian Optimization framework (CMFBO) for efficient hyperparameter optimization of DRL-based character control systems. Using curriculum-based task difficulty as fidelity criterion, our method improves searching efficiency by gradually pruning search space through evaluation on easier motor skill tasks. We evaluate our method on two physics-based character control tasks: character morphology optimization and hyperparameter tuning of DeepMimic. Our algorithm significantly outperforms state-of-the-art hyperparameter optimization methods applicable for physics-based character animation. In particular, we show that hyperparameters optimized through our algorithm result in at least 5x efficiency gain comparing to author-released settings in DeepMimic.

published in ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games 2021

References in corpus (7)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Emergence of Locomotion Behaviours in Rich Environments
• Scalable Bayesian Optimization Using Deep Neural Networks
• Freeze-Thaw Bayesian Optimization
• Multi-fidelity Bayesian Optimisation with Continuous Approximations
• Sequential Gallery for Interactive Visual Design Optimization
• Neural fidelity warping for efficient robot morphology design