An open API service indexing awesome lists of open source software.

https://github.com/adityajn105/move37

Move37 is a Reinforcement Learning Course by Siraj Raval's The School of AI. This repository is to maintain all codes done during this course.
https://github.com/adityajn105/move37

markov-decision-processes reinforcement-learning tensorflow

Last synced: 3 months ago
JSON representation

Move37 is a Reinforcement Learning Course by Siraj Raval's The School of AI. This repository is to maintain all codes done during this course.

Awesome Lists containing this project

README

          

# Move37
Move37 is a 10-week Reinforcement Learning Course by The School of AI. This is a repository to maintain all codes for homework assignments and Projects done during this course.

## Week 1 - Markov Decision Processes
1. The Bellman Equation
2. * Markov Decision Process *
3. Value Functions
4. Homework - OpenAI Gym Installation and Basics
5. Sensor Networks
6. Google Dopamine

## Week 2 - Dynamic Programming
1. Sports Betting
2. * Bellman Advanced *
3. Dynamic Programming tutorial
4. Dynamic Programming Reading Assignments
5. * Value and Policy Iterations *
6. Homework - Frozen Lake Problem with Value and Policy Iterations
7. IPhoneX supply chain

## Week 3 - Monte Carlo Methods
1. Internet of Things Optmisation
2. Exploration vs Exploitation
3. Exploration vs Exploitation (Multi Arm Bandits)
4. Monte Carlo Coding Tutorial
5. * MC Control and MC Prediction *
6. Monte Carlo Methods
7. Q Learning for trading
8. Homework Assignment - Monte Carlo
9. Tensor Processing Units

## Week 4 - Model Free Learning
1. Dopamine in Neuroscience
2. * Reading Assignments - Model Based vs Model Free Learning *
3. Homework Assignment (Q Learning)
4. * Temporal Difference Learning *
5. Q Learning for Ride Sharing
6. Quantum Interview

## Week 5 - RL in Continuous Spaces
* Skipped *

## Week 6 - Deep Reinforcement Learning
1. Deep RL for Database Optimization
2. Deep Q Learning Pong Tutorial
3. * Prioritized Experience Replay (PER) *
4. Dueling DQN
5. Neural Networks Study Guide
6. Neural Networks Quiz
7. * Reading Assignment (DQN Improvements) *
8. Homework Assignment (Deep Q Learning)

## Week 7 - Policy Based Methods
1. * Neuroevolution Meta-Learning *
2. Policy Search Algorithms
3. * Evolutionary Algorithms Study Guide *
4. Homework Assignment (Neuroevolution)
5. Control Theory

## Week 8 - Policy Gradient Methods
1. Policy Gradients Math Primer
2. Policy Gradient Methods Tutorial
3. Policy Gradient methods (REINFORCE)
4. Evolved Policy Gradients
5. * Policy Gradients Study Guide *
6. Homework Assignment (Monte Carlo Policy Gradients)
7. Artificial Curiosity

## Week 9 - Actor Critic Methods
1. Drone Flight Controller
2. Asynchronous Advantage Actor Critic (A3C) Tutorial
3. * Reading Assignment (Actor Critic Algorithms) *
4. Homework Assignment (A2C)
5. Continuous Action Space Actor Critic Tutorial
6. * Master Roboschool with PPO (Coding Tutorial) *
7. * PPO (Proximal Policy Optimization) *
8. Bayesian Actor Critic
9. Actor Critic Methods Study Guide

## Week 10 - Multi Agent RL
1. Move37
2. Reading Assignment (Cooperative Agents)
3. Inverse Reinforcement Learning
4. MARL – Multi Agent Reinforcement Learning
5. Multi Agent and Inverse RL Study Guide
6. AlphaGo Zero Tutorial Part 3 – Neural Network Architecture
7. Final Project (Multi Agent Research Project)