Does RLzoo support Dict gym env state?

[GIS-PuppetMaster]

My customized gym env has a dict type obs_space, even I also customized ActorNetwork and CriticNetwork, I found out RLzoo's source code seems only support single input and can not handle dict state. Is there any plan to support dict gym env state?

[quantumiracle]

Hi, It supports dict state, but you need a wrapper for your env. Please take a look at the FlattenDictWrapper (./common/env_wrappers.py) for robotics env.

[GIS-PuppetMaster]

Hi, It supports dict state, but you need a wrapper for your env. Please take a look at the FlattenDictWrapper (./common/env_wrappers.py) for robotics env.

Thanks, I think maybe supporting a preprocessing class like keras-rl is more flexible.