GitHub - ThermalSoaring/Machine-Learning-Policy-Formation: Dynamic programming / Q learning policy - table based and with neural interpolation.

Name		Name	Last commit message	Last commit date
Latest commit History 17 Commits
__pycache__		__pycache__
contThermalEnvironment.py		contThermalEnvironment.py
evalPolicy.py		evalPolicy.py
learnerCustom.py		learnerCustom.py
main.py		main.py
main_modelBased.py		main_modelBased.py
modelBased1D.py		modelBased1D.py
simpleThermal.py		simpleThermal.py
simpleThermalEnvironment.py		simpleThermalEnvironment.py
simpleThermalTask.py		simpleThermalTask.py
tabledBasedMethods.py		tabledBasedMethods.py
updatePolicy.py		updatePolicy.py