/Reinforcement-Learning-Specialization

Reinforcement Learning Specialization on Coursera

Primary LanguageJupyter Notebook

Reinforcement Learning Specialization

This repository contains the assignments done as a part of the Reinforcement Learning Specialization offered by University of Alberta on Coursera.

You can view the course by clicking on this link.

This repo consists of the following implementations:

  1. K-Armed Bandits
  2. Dynamic Programming for Policy Iteration and Improvement
  3. Temporal Differnce Learning
  4. Q-Learning and SARSA
  5. Dyna-Q and Dyna-Q+
  6. TD with State Aggregation
  7. Semi-Gradient TD
  8. Function Approximation and Control using Tile Coding-SARSA
  9. Actor-Critic using TD(0)

References:

  1. Reinforcement Learning: An Introduction
  2. Lectures by David Silver
  3. Advanced Deep Learning and Reinforcement Learning
  4. List of RL algorithms and their implementations
  5. Stanford CS234: Reinforcement Learning