Deep_Reinforcement_Learning

Working through and expanding upon examples from 'Deep Reinforcement Learning Hands-On' by Maxim Lapan

  • 00_xbvf_cartpole_testing: Script to test video recording of agent's behavior.

  • 01_Atari_image_GAN: Generator learn how to create authentic Atari screenshots in ~50,000 iterations.

  • 02_cartpole_cross_entropy: Uses crossentropy RL method to teach the agent to balance a pole.

  • 03_frozen_lake_entropy: Navigating a slippery maze using cross-entropy.

  • 04_frozen_lake_value_iteration: Navigating the slippery lake with value iteration.

  • 05_frozen_lake_q_learning: Navigating the slippery lake with q learning.