Homework of the Deep Reinforcement Learning course by Anton Plaksin.

In these HW covered the assigments

• Cross-Entropy Method
• Deep Cross-Entropy Method
• Policy and Value Iterations
• Monte-Carlo, SARSA, Q-Learning

Built the code base to run multiple experiments and analyze the result.

Homework 3 - Lunar lander - that was fun miniproject from HW2. The goal was to visualize the learnin process of the agent.