Efficient Hyperparameter Optimization for Physics-based Character Animation

by   Zeshi Yang, et al.

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.


page 1

page 2

page 3

page 4


Bayesian Optimization for Iterative Learning

The success of deep (reinforcement) learning systems crucially depends o...

Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning

Reinforcement learning algorithms can show strong variation in performan...

Deep Reinforcement Learning using Cyclical Learning Rates

Deep Reinforcement Learning (DRL) methods often rely on the meticulous t...

Hyperparameter Optimization via Sequential Uniform Designs

Hyperparameter tuning or optimization plays a central role in the automa...

Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations

The Generative Adversarial Network (GAN) is a powerful and flexible tool...

FLO: Fast and Lightweight Hyperparameter Optimization for AutoML

Integrating ML models in software is of growing interest. Building accur...

Discrete Simulation Optimization for Tuning Machine Learning Method Hyperparameters

Machine learning methods are being increasingly used in most technical a...

Please sign up or login with your details

Forgot password? Click here to reset