/RL-Coursera

Implementations of Coursera Reinforcement Learning Specialization

Primary LanguageJupyter NotebookMIT LicenseMIT

RL-Coursera

Implementations of Coursera Reinforcement Learning Specialization.

The structure of this specialization:

drawing

1. Fundamentals of Reinforcement Learning

Week 2: Markov Decision Processes

Week 3: Value Functions & Bellman Equations

  • No assignment

Week 4: Dynamic Programming

2. Sample-based Learning Methods

Week 2: Monte Carlo Methods for Prediction & Control

  • No assignment

Week 3: Temporal Difference Learning Methods for Prediction

Week 4: Temporal Difference Learning Methods for Control

Week 5: Planning, Learning & Actiong

3. Predictions and Control with Function Approximation

Week 1: On-policy Prediction with Approximation

Week 2: Constructing Features for Prediction

Week 3: Function Approximation and Control

Week 4: Policy Gradient

4. A Complete Reinforcement Learning System (Capstone)

Lunar Lander Projects