Modify for non-pixel inputs

toshikwa / slac.pytorch

PyTorch implementation of Stochastic Latent Actor-Critic(SLAC).

MIT License

87 stars 16 forks source link

Modify for non-pixel inputs #8

Closed hai-h-nguyen closed 3 years ago

hai-h-nguyen commented 3 years ago

Do you know how can I start to modify the code to work with non-pixel inputs?

toshikwa commented 3 years ago

Hi @hai-h-nguyen

Because SLAC is focusing on high-dimensional observation by explicitly learning latent representations, I don't think it's a good approach to apply it to the low-dimensional observation.

What kind of problem do you want to solve?