Grid_World

Warning: code maybe not applicable, more of personal scripts without good structures.

A simple demo during Reinforcement Learning study.

Algorithm included:

• Policy Evaluation

• Value Iteration

• Policy Iteration

• Truncated Policy Iteration

  ---

• Monte-Carlo(MC) Search

• Monte-Carlo(MC) Basic Policy Evaluation

• Monte-Carlo(MC) ε-Greedy

  ---

• Sarsa

• Q-learning[on-policy]

• Q-learning[off-policy]

  ---

• Deep Q-Network(DQN)

• Advantage Actor-Critic(A2C)