My implementation of Easy21 (WIP)

My implementation of the Easy21 programming exercise using Reinforcement Learning, from David Silver's excellent 2015 Reinforcement Learning course.

Instructions:

1. Run pip install . in the same directory as the setup.py file.

See the demo_environment.ipynb for sample usage. Note that this environment was built and tested with Python 3.10 and numpy.

MonteCarloControl.ipynb demos what happens when Monte Carlo Control is run. TD_Learning.ipynb is the equivalent for TD learning