MDPs - Markov Decision Processes - Decision Making Under Uncertainty Using POMDPs.jl

This course on Decision Making Under Uncertainty using POMDPs.jl aims to teach learners about Markov Decision Processes (MDPs) and how to make decisions under uncertainty. By the end of the course, students will be able to understand MDP definitions, state and action spaces, transition and reward functions, discount factors, and how to use tools like QuickPOMDPs, MDP solvers, and RL solvers. The course covers topics such as Value iteration, Transition probability distribution, Reinforcement learning with TD learning, Q-learning, and SARSA. The teaching method includes theoretical explanations, practical examples using Grid World environments, visualizations, and simulations. This course is intended for individuals interested in decision-making processes, reinforcement learning, and using Julia programming language for solving problems under uncertainty.