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:
- K-Armed Bandits
- Dynamic Programming for Policy Iteration and Improvement
- Temporal Differnce Learning
- Q-Learning and SARSA
- Dyna-Q and Dyna-Q+
- TD with State Aggregation
- Semi-Gradient TD
- Function Approximation and Control using Tile Coding-SARSA
- Actor-Critic using TD(0)
References: