Beniamin BOGOSEL

Reinforcement Learning

In this course we will explore basic aspects in Reinforcement Learning. The course is inspired by the following GitHub repository: https://github.com/johnnycode8/gym_solutions.

• Course 1: Frozen Lake environment in Gymnasium. Q-learning basics. Notebook: file
• Course 2: Frozen Lake environment: enhanced. Q-learning basics (continued) Python files:
  • frozen_lake_enhanced.py
  • Main file to run: frozen_lake_qe.py
• Course 3-4: Q-learning continued: taxi environment, mountain car
• Course 5-6: Quick introduction to neural networks with PyTorch. See the following notebooks:
  • Notebook 1
  • Notebook 2
• Course 7 Deep Q learning: python file
• Course 8 Deep Q learning:
  • Mountain Car - Q learning
  • Mountain Car - DQL Simple
  • Mountain Car - DQL Double
  • Mountain Car - DQL Simple Batch
  • Mountain Car - DQL Double
  • Mountain Car - DQL Plot Learned
• Course 9
  • DQL_Cart_Pole
  • DQL_Cart_Pole_Middle
  • DQL_Acrobot
  • DQL Acrobot Shaped Reward
  • DQL_Lunar
  • DQL_Lunar_Eng
• Course 10
  • Dueling Deep Q Networks: Markdown file
  • Codes: DeepQLFlappy.zip
  • Source: https://github.com/johnnycode8/dqn_pytorch