Syllabus

1. Markov Decision Processes

   • Introduction
   • Sensor Networks
   • Supply Chain Management
   • Energy Efficiency
   • Reading Assignment (Policy Functions)
   • Homework Assignment (Bellman Equation)
   • Markov Decision Processes
   • The Bellman Equations

2. Dynamic Programming

   • Route Planning
   • Options Pricing
   • Scheduling
   • Operating Systems
   • Reading Assignment (History of DP)
   • Homework Assignment (Value Iteration)
   • Dynamic Programming

3. Monte Carlo Methods

   • Medical Diagnosis
   • Network Routing Optimization
   • Physics Research
   • Reading Assignment (Exploration vs Exploitation)
   • Homework Assignment (Greedy Policies)
   • MC Prediction and MC Control

4. Model Free Learning

   • Delivery Management
   • Automated Trading
   • Backgammon
   • Dopamine in Neuroscience
   • Reading Assignment (SARSA)
   • Homework Assignment (Q Learning)
   • Temporal Difference Learning

5. RL in Continuous Spaces

   • Self Driving Cars
   • Delivery Drones
   • Rescue Robots
   • Assembly Robots
   • Reading Assignment (Control Theory)
   • Midterm Assignment (Make a Bipedal Robot Walk )
   • Continuous Space Techniques

6. Deep Reinforcement Learning

   • Traffic Optimization
   • Gaming
   • Meta Learning
   • Homework Assignment (Deep Q Learning)
   • Reading Assignment (DQN Improvements)
   • The Evolution of Deep Q Learning

7. Policy Based Methods

   • Web System Configuration
   • Text Summarization
   • AI Assisted Design
   • Portfolio Optimization
   • Reading Assignment (Evolutionary Algorithms)
   • Homework Assignment (REINFORCE)
   • Stochastic Policy Search

8. Policy Gradient Methods

   • Dialogue Systems
   • Photo Editing
   • Language Translation
   • Tutoring Systems
   • Reading Assignment (Evolved Policy Gradients)
   • Homework Assignment (TRPO)
   • Generalized Advatange Estimation

9. Actor Critic Methods

   • Advanced Trading Techniques
   • Human-Machine Cooperation
   • Insurance Cost Analysis
   • Reading Assignment (Actor Critic Algorithms)
   • Homework Assignment (Bayesian Actor Critic)
   • Asynchronous Advantage Actor Critic

10. Multi Agent RL

    • Move 37
    • Transporation Networks
    • Decentralized Autonomous Organizations
    • The Future of AI
    • Reading Assignment (Cooperative Agents)
    • Inverse Reinforcement Learning
    • Final Project (Multi Agent Research Project)