commonpower.control.wrappers
Wrappers to adjust API in environments.py to different RL training algorithms.
Functions
Transforms the orginal dict of the controller assignments to a list of lists. |
|
Reverses the transform_to_ordered_dict_keys function. |
|
Recursive extraction of all values in a nested dictionary or gym.spaces.Dict |
Classes
Wrapper to standardize the deployment within CommonPower. |
|
Wrapper to standardize ControlEnv to the API for MAPPO/IPPO implementation of the on-policy repository (https://github.com/marlbenchmark/on-policy/tree/main/onpolicy). |
|
Wrapper for recording transition tuples (s,a,s',r) either to current disk or to a data base. |
|
Wrapper to standardize ControlEnv to the API for single-agent RL training with any RL algorithm from the StableBaselines 3 repository. |
|