This reposity contains my solutions for the programming assignments from all courses in the Reinforcement Learning Specialization offered by University of Alberta in Coursera.
- Assignment 1: Bandits and Exploration/Exploitation
- Assignment 2: Optimal Policies with Dynamic Programming
- Assignment 1: Blackjack
- Assignment 2: Policy Evaluation with Temporal Difference Learning
- Assignment 3: Q-Learning and Expected Sarsa
- Assignment 4: Dyna-Q and Dyna-Q+
- Assignment 1: Semi-gradient TD(0) with State Aggregation
- Assignment 2: Semi-gradient TD with a Neural Network
- Assignment 3: Function Approximation and Control
- Assignment 4: Average Reward Softmax Actor-Critic using Tile-coding
- Assignment 1: Setting the Reward Function
- Assignment 2: Implement Your Agent
- Assignment 3: Completing the parameter study