Provides wrappers for single and multi-agent RLlib algorithms. Major updates to the CLI to support CityLearn and Stable-Baselines3 agents as well as path name defined agents that inherit and use the same interface as CityLearn or Stable-Baselines3 agents.
Issue
Resolves #103
Changes
Wrapper support for RLlib single and multi-agent.
RLlib examples added to quickstart notebook.
add read/write functions for YAML and Pickle files.
Added option to log out of bound observations and added citylearn.wrappers.ClippedObservationWrapper wrapper to clip observations to their space limits.
Improvements to CLI interface to allow more environment, reward and agent customization from Terminal.
Added CLI page to docs.
Reduced actions Python environment to 3.11.
Screenshots
NIL
Checklist
[x] I have tested the changes locally and they work as intended.
[x] I have updated the documentation, if applicable.
[ ] I have added new tests, if applicable.
[x] I have added any required dependencies to the requirements.txt file, if applicable.
[x] I have followed the project's code style and conventions.
Description
Provides wrappers for single and multi-agent RLlib algorithms. Major updates to the CLI to support CityLearn and Stable-Baselines3 agents as well as path name defined agents that inherit and use the same interface as CityLearn or Stable-Baselines3 agents.
Issue
Resolves #103
Changes
citylearn.wrappers.ClippedObservationWrapperwrapper to clip observations to their space limits.Screenshots
NIL
Checklist
requirements.txtfile, if applicable.Additional notes
NIL