• Course Number: EE 4660
• Year: 2020-Spring

This course introduces some basic Reinforcement Learning knowledge without complicated mathematical derivation, and focuses on implementing classic algorithms from scratch.

• Multi-Armed Bandit

  Get familiar with basic action-value based methods in multi-armed bandit problems.

• Grid World

  By Bellman Equation method to find optimal value function

• Grid World

  Use dynamic programming to find an optimal policy

• Swamp

  Monte Carlo control algorithm implementation

• Swamp

  One step TD method, including Sarsa and Q-learning

• Swamp

  n step TD method, mainly on 5-step Sarsa implementation

• Swamp

  Planning and Learning with Tabular Methods, mainly on Dyna-Q algorithm

• Mountain Car

  Control with Function Approximation method