This repository contains source code (helper.py) and materials related to the task of dynamic programming - policy iteration.
The task is derived from the Reinforcement Learning Classes course. The full materials and instructions for this task can be found at: https://github.com/PrzemekSekula/ReinforcementLearningClasses/tree/main/DynamicProgramming.
In this task, I implement policy iteration in the context of dynamic programming. The policy iteration algorithm involves iteratively updating state values and improving the policy to find an optimal strategy.
To see the example usage of the policy iteration algorithm, open the policy_iteration.ipynb.