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.

中文翻译：

---

基于物理的角色动画的高效超参数优化

近年来，随着深度强化学习（DRL）的采用，基于物理的角色动画取得了长足的进步。但是，基于DRL的学习方法通​​常在计算上昂贵，并且其性能关键取决于超参数的选择。调整这些方法的超参数通常需要重复训练控制策略，这在计算上甚至更加令人望而却步。在这项工作中，我们提出了一种新颖的基于课程的多保真贝叶斯优化框架（CMFBO），用于基于DRL的字符控制系统的高效超参数优化。我们的方法以课程为基础的任务难度作为保真度标准，通过对较简单的运动技能任务进行评估来逐步修剪搜索空间，从而提高了搜索效率。我们在两个基于物理学的字符控制任务上评估了我们的方法：字符形态优化和DeepMimic的超参数调整。我们的算法大大优于适用于基于物理的角色动画的最新超参数优化方法。尤其是，我们证明，与DeepMimic中作者发布的设置相比，通过我们的算法优化的超参数至少可将效率提高5倍。