search

facebookresearch / ScaDiver

Project for the paper "A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters"
Other
155 stars 18 forks source link

How were the reward hyperparameters obtained? #5

Closed ManifoldFR closed 4 years ago

ManifoldFR commented 4 years ago

Hi,

I read the paper and looked through the code. I am wondering how the parameters (lengthscales, for instance) for the reward kernels and the reward tree were obtained. Was it some rule of thumb? I guess random search or using optuna is a possibility, but that would be expensive, right?

Thanks.

Jungdam commented 4 years ago

Hi,

In case of some reference values are available (e.g., similar terms in Peng 2018 or Park 2019), I first adopted the values in those references then modified them accordingly. Otherwise, I choose parameters experimentally from scratch, where my rule of thumb is to make all the terms be equal as possible then modify the values according to the achieved results.

ManifoldFR commented 4 years ago

Thanks !