I am attending Siraj's Move 37 course through the School of AI. This repository contains my notes and assignments as I work through his course. I also use it to gather and track all resources Siraj provides us through his course.
- Week 01 Notes: Markov Decision Processes
- Week 02 Notes: Dynamic Programming
- Week 03 Notes: Monte Carlo Methods
- Week 04 Notes: Model Free Learning
- Week 05 Notes: RL in Continuous Spaces
- Week 06 Notes: Deep Reinforcement Learning
- Week 07 Notes: Policy Based Methods
- Week 08 Notes: Policy Gradient Methods
- Week 09 Notes: Actor-Critic Methods
- Week 10 Notes: Multi Agent RL
- Homework 01: OpenAI Gym Installation
- Homework 02: Value & Policy Iteration
- Homework 03: Monte Carlo
- Homework 04: Q Learning
- Midterm: Make a Bipedal Robot Walk
- Homework 06: Deep Q Learning
- Homework 07: Neuroevolution
- Homework 08: Policy Gradient Methods
This is the syllabus for "Move 37", Siraj Raval's free reinforcement learning course, as part of School of AI. This course can be taken for free on Youtube in the form of a playlist, or at School of AI for a more immersive learning experience. Reinforcement learning is driving some of the latest advances in AI, from DeepMind's AlphaGo to OpenAI's DOTA bots. Although these AIs are designed for video games, reinforcement learning is a powerful branch of AI that can be applied to endless applications in the real world. In this course, we'll cover various RL techniques in order of increasing complexity, applying them to both simulated and real world problems. Students will develop an intuition around when to use certain RL algorithms and by the end of the course will have the practical skills necessary to apply RL to a problem they are passionate about to make a positive impact in the world.
- Understand Basic Python Syntax
- Understand how the Backpropagation algorithm works.
- Midterm Project
- Final Project
- Educational Videos
- Quizzes
- Reading Assignments
- Coding Assignments
- Interviews
- Group Discussion in Slack
- 10 Weeks
- 10-15 hours of dedicated study per week
- Starts September 10 at 12 PM PST
- Pytorch & Tensorflow (Deep Learning Libraries in Python)
- OpenAI Gym (Reinforcement Learning Library)
- Google Colab (for free GPUs, no need to install/configure dependencies)
- Route Planning
- Options Pricing
- Scheduling
- Operating Systems
- Interview #1
- Medical Diagnosis
- Energy Efficiency
- Physics Research
Monte Carlo prediction, Monte Carlo control, Greedy & Epsilon-Greedy Policies , Exploration vs Exploitation Dilemma
- Delivery Management
- Automated Trading
- Backgammon
- Dopamine in Neuroscience
- Self Driving Cars
- Delivery Drones
- Rescue Robots
- Assembly Robots
- Train a bipedal humanoid robot to walk in simulation!
- Traffic Optimization
- Gaming
- Meta Learning
- Interview #2
- Web System Configuration
- Text Summarization
- AI Assisted Design
- Portfolio Optimization
- Dialogue Systems
- Photo Editing
- Language Translation
- Tutoring Systems
Evolved Policy Gradients, Generalized Advantage Estimation (GAE), Trust Region Policy Optimization, Proximal Policy Optimization (PPO)
- Advanced Trading Techniques
- Human-Machine Cooperation
- Insurance Cost Analysis
- Interview #3
Actor Critic Algorithms, Asynchronous Advantage Actor Critic, Deep Deterministic Policy Gradients (DDPG), Bayesian Actor-Critic
- Move 37
- Transportation Networks
- Decentralized Autonomous Organizations
- The Future of AI
- Develop a multi-agent network to solve a real world problem!