v1.2.0 Release: Model Update and Improvements

This release introduces general improvements and updates both the ML and the RL model.

General:

• Most importantly, the interface to use both models has changed. Please have a look at the readme.

ML Model Update:

• Provided more training data (3000 instead of 2000 samples).
• Provided the accordingly trained Random Forest Classifier.
• More information of the predicted combination of compilation options is returned.
• The performance evaluation is extended.

RL Model Update:

• Provided more training data (500 instead of 200 samples).
• Improved the observation space representation.
• The trained RL models are not part of the repository itself anymore, but are downloaded when needed at runtime.
• Two more reward functions are introduced and evaluated.

What's Changed

• ML Improvements in #59
• Rl improvements in #61

Full Changelog: v1.1.1...v1.2.0