/Coding_Reinforcement_Learning

Implementation of basic RL steps and algorithms - Dynamic Programming approach, Monte-Carlo approach, DQN on Atari, Policy Gradient - Reinforce with baseline, Actor Critic (A2C)

Primary LanguageJupyter NotebookMIT LicenseMIT

Coding the RL elements

Implementation of basic RL steps and algorithms with my personal snippets/notes in jupyter notebook.

References -

  1. Intro to RL - Sutton & Barto
  2. Denny Britz RL Repo - blackjack.py, gridworld.py, plotting.py