The differences between `env_batch` and `batch_size`

hzwer / ICCV2019-LearningToPaint

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

MIT License

2.25k stars 312 forks source link

The differences between `env_batch` and `batch_size` #28

Closed Vandermode closed 4 years ago

Vandermode commented 4 years ago

Hi, I dived into the code of your paper and I'm confused of the two variables env_batch and batch_size, which seems to be the same according to your implementation.

Could you give me some hints to help me figure it out? Thank you very much

hzwer commented 4 years ago

env_batch refers to how many strokes are generated each time when interacting with the environment. batchsize is the number of samples per gradient descent.

Vandermode commented 4 years ago

Thank you for your response! but I'm still wondering about the benefit of such a design choice. Why not directly set env_batch = batchsize?

hzwer commented 4 years ago

Because there is no discriminator when inference, GPU memory usage is different. Moreover, the proportion of time for training and environment interaction can be adjusted.