Reinforcement Learning Specialization

Responsible	Administrator
Last Update
Members	1

Course
Reviews

Advanced

1. Course Introduction
- 1. Specialization Introduction.mp4
  
  Preview
- 2. Course Introduction.mp4
  
  Preview
- 3. Meet your instructors!.mp4
  
  Preview
- 4. Your Specialization Roadmap.mp4
  
  Preview
- 5. Reinforcement Learning Textbook.pdf
  
  Preview
- 6. Fundamentals of Reinforcement Learning.pdf
  
  Preview
2. The K-Armed Bandit Problem
- 1. Sequential Decision Making with Evaluative Feedback.mp4
  
  Preview
3. What to Learn? Estimating Action Values
- 1.Learning Action Values.mp4
  
  Preview
- 2.Estimating Action Values Incrementally.mp4
  
  Preview
4. Exploration vs. Exploitation Tradeoff
- 1.What is the trade-off?.mp4
  
  Preview
- 2.Optimistic Initial Values.mp4
  
  Preview
- 3. Upper-Confidence Bound (UCB) Action Selection.mp4
  
  Preview
- 4.Jonathan Langford Contextual Bandits for Real World Reinforcement Learning.mp4
  
  Preview
- 5.Week 1 Summary.mp4
  
  Preview
Programming Assignment: Bandits and Exploration Exploitation
- Assignment1.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2.png
  
  Preview
- 3.png
  
  Preview
- 4.png
  
  Preview
- 5.png
  
  Preview
- 6-7.png
  
  Preview
- 8.png
  
  Preview
1. Introduction to Markov Decision Processes
- 1.Markov Decision Processes.mp4
  
  Preview
- 2.Examples of MDPs.mp4
  
  Preview
2. Goal of Reinforcement Learning
- 1.The Goal of Reinforcement Learning.mp4
  
  Preview
- 2.Michael Littman The Reward Hypothesis.mp4
  
  Preview
3. Continuing Tasks
- 1.Continuing Tasks.mp4
  
  Preview
- 2.Examples of Episodic and Continuing Tasks.mp4
  
  Preview
- 3.Week 2 Summary.mp4
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5-6.png
  
  Preview
- 7-8.png
  
  Preview
- 9-10.png
  
  Preview
- 11-12.png
  
  Preview
1. Policies and Value Functions
- 1.Specifying Policies.mp4
  
  Preview
- 2.Value Functions.mp4
  
  Preview
- 3.Rich Sutton and Andy Barto A brief History of RL.mp4
  
  Preview
2. Bellman Equations
- 1.Bellman Equation Derivation.mp4
  
  Preview
- 2.Why Bellman Equations .mp4
  
  Preview
3. Optimality (Optimal Policies & Value Functions)
- 1.Optimal Policies.mp4
  
  Preview
- 2. Optimal Value Functions.mp4
  
  Preview
- 3.Using Optimal Value Functions to Get Optimal Policies.mp4
  
  Preview
- 4.Week 3 Summary.mp4
  
  Preview
Graded Quiz
- 1.png
  
  Preview
- 2.png
  
  Preview
- 3-4-5.png
  
  Preview
- 6-7-8.png
  
  Preview
- 9-10.png
  
  Preview
- 11.png
  
  Preview
Practice Quiz
- 1-2-3-4.png
  
  Preview
- 5-6-7-8.png
  
  Preview
- 9-10.png
  
  Preview
1. Policy Evaluation (Prediction)
- 1.Policy Evaluation vs. Control.mp4
  
  Preview
- 2.Policy Evaluation vs. Control.mp4
  
  Preview
2. Policy Iteration (Control)
- 1.Policy Improvement.mp4
  
  Preview
- 2.Policy Iteration.mp4
  
  Preview
3. Generalized Policy Iteration
- 1.Flexibility of the Policy Iteration Framework.mp4
  
  Preview
- 2.Efficiency of Dynamic Programming.mp4
  
  Preview
- 3.Warren Powell Approximate Dynamic Programming for Fleet Management (Short).mp4
  
  Preview
- 4.Warren Powell Approximate Dynamic Programming for Fleet Management (Long).mp4
  
  Preview
- 5.Week 4 Summary.mp4
  
  Preview
4. Course Wrap-up
- Congratulations!.mp4
  
  Preview
Programming Assignment: Optimal Policies with Dynamic Programming
- Assignment2.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5-6-7.png
  
  Preview
- 8-9.png
  
  Preview
- 10.png
  
  Preview
1. Course Introduction
- 1.Course Introduction.mp4
  
  Preview
- 2.Meet your instructors!.mp4
  
  Preview
- VS1fBbZLEemddAqBQMk_og_e4f640a64cee4a4abc80b9480ec692cd_Course-2_-Sample-Based-Learning-Methods-Learning-Objectives-.pdf
  
  Preview
2. Introduction to Monte Carlo Methods
- 1.What is Monte Carlo .mp4
  
  Preview
- 2.Using Monte Carlo for Prediction.mp4
  
  Preview
3. Monte Carlo for Control
- 1.Using Monte Carlo for Action Values.mp4
  
  Preview
- 2.Using Monte Carlo methods for generalized policy iteration.mp4
  
  Preview
- 3.Solving the Blackjack Example.mp4
  
  Preview
4. Exploration Methods for Monte Carlo
- 1.Epsilon-soft policies.mp4
  
  Preview
5. Off-policy Learning for Prediction
- 1.Why does off-policy learning matter .mp4
  
  Preview
- 2.Importance Sampling.mp4
  
  Preview
- 3.Off-Policy Monte Carlo Prediction.mp4
  
  Preview
- 4.Emma Brunskill Batch Reinforcement Learning.mp4
  
  Preview
- 5.Week 1 Summary.mp4
  
  Preview
Programming Assignment: Blackjack
- Blackjack.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5.png
  
  Preview
- 6-7-8.png
  
  Preview
- 9-10.png
  
  Preview
1. Introduction to Temporal Difference Learning
- 1.What is Temporal Difference (TD) learning .mp4
  
  Preview
- 2.Rich Sutton The Importance of TD Learning.mp4
  
  Preview
2. Advantages of TD
- 1.The advantages of temporal difference learning.mp4
  
  Preview
- 2.Comparing TD and Monte Carlo.mp4
  
  Preview
- 3.Andy Barto and Rich Sutton More on the History of RL.mp4
  
  Preview
- 4.Week 2 Summary.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5-6.png
  
  Preview
- 7-8.png
  
  Preview
- 9.1.png
  
  Preview
- 9.2.png
  
  Preview
- 10-11.png
  
  Preview
1.TD for Control
- 1.Sarsa GPI with TD.mp4
  
  Preview
- 2.Sarsa in the Windy Grid World.mp4
  
  Preview
2. Off-policy TD Control: Q-learning
- 1.What is Q-learning .mp4
  
  Preview
- 2.Q-learning in the Windy Grid World.mp4
  
  Preview
- 3.How is Q-learning off-policy .mp4
  
  Preview
3. Expected Sarsa
- 1.Expected Sarsa.mp4
  
  Preview
- 2.Expected Sarsa in the Cliff World.mp4
  
  Preview
- 3.Generality of Expected Sarsa.mp4
  
  Preview
- 4.Week 3 Summary.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2-3-4.png
  
  Preview
- 5-6-7-8-9.png
  
  Preview
1. What is a Model?
- 1.What is a Model .mp4
  
  Preview
- 2.Comparing Sample and Distribution Models.mp4
  
  Preview
2. Planning
- 1.Random Tabular Q-planning.mp4
  
  Preview
3. Dyna as a formalism for planning
- 1.The Dyna Architecture.mp4
  
  Preview
- 2.The Dyna Algorithm.mp4
  
  Preview
- 3.Dyna & Q-learning in a Simple Maze.mp4
  
  Preview
4. Dealing with inaccurate models
- 1.What if the model is inaccurate .mp4
  
  Preview
- 2.In-depth with changing environments.mp4
  
  Preview
- 3. Drew Bagnell self-driving, robotics, and Model Based RL.mp4
  
  Preview
- 4.Week 4 Summary.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
5. Course Wrap-up
- Congratulations!.mp4
  
  Preview
Quiz
- 1-2.png
  
  Preview
- 3-4.png
  
  Preview
- 5.png
  
  Preview
- 6-7.png
  
  Preview
- 8.png
  
  Preview
- 9.1.png
  
  Preview
- 9.2.png
  
  Preview
- 9.png
  
  Preview
- 10.png
  
  Preview
1. Course 3 Introduction
- 1. Course 3 Introduction.mp4
  
  Preview
- 2.Meet your instructors!.mp4
  
  Preview
- kcjGf-C0Eem3eBKX1RzcIA_799ef7d4980742a4bdadc73a4fd52958_Prediction-and-Control-with-Function-Approximation-Learning-Objectives.pdf
  
  Preview
2. Estimating values functions with supervised learning
- 1.Moving to Parameterized Functions.mp4
  
  Preview
- 2.Generalization and Discrimination.mp4
  
  Preview
- 3.Framing Value Estimation as Supervised Learning.mp4
  
  Preview
3. The Objective for On-policy Prediction
- 1.The Value Error Objective.mp4
  
  Preview
- 2.Introducing Gradient Descent.mp4
  
  Preview
- 3.Gradient Monte for Policy Evaluation.mp4
  
  Preview
- 4.State Aggregation with Monte Carlo.mp4
  
  Preview
4. The Object for TD
- 1.Semi-Gradient TD for Policy Evaluation.mp4
  
  Preview
- 2.Comparing TD and Monte Carlo with State Aggregation.mp4
  
  Preview
- 3.Doina Precup Building Knowledge for AI Agents with Reinforcement Learning.mp4
  
  Preview
5. Linear TD
- 1.The Linear TD Update.mp4
  
  Preview
- 2.The True Objective for TD.mp4
  
  Preview
- 3.The True Objective for TD.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5.png
  
  Preview
- 6-7.png
  
  Preview
- 8-9-10.png
  
  Preview
- 11-12.png
  
  Preview
1. Feature Construction for Linear Methods
- 1.Coarse Coding.mp4
  
  Preview
- 2.Generalization Properties of Coarse Coding.mp4
  
  Preview
- 3.Tile Coding.mp4
  
  Preview
- 4.Using Tile Coding in TD.mp4
  
  Preview
2. Neural Networks
- 1.What is a Neural Network .mp4
  
  Preview
- 2.Non-linear Approximation with Neural Networks.mp4
  
  Preview
- 3.Deep Neural Networks.mp4
  
  Preview
3. Training Neural Networks
- 1.Gradient Descent for Training Neural Networks.mp4
  
  Preview
- 2.Optimization Strategies for NNs.mp4
  
  Preview
- 3.David Silver on Deep Learning + RL = AI .mp4
  
  Preview
- 4.Week 2 Review.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2.png
  
  Preview
- 3-4-5.png
  
  Preview
- 6-7-8.png
  
  Preview
- 9.png
  
  Preview
- 10.png
  
  Preview
- 11-12.png
  
  Preview
1. Episodic Sarsa with Function Approximation
- 1.Episodic Sarsa with Function Approximation.mp4
  
  Preview
- 2.Episodic Sarsa in Mountain Car.mp4
  
  Preview
- 3.Expected Sarsa with Function Approximation.mp4
  
  Preview
2. Exploration under Function Approximation
- 1.Exploration under Function Approximation.mp4
  
  Preview
3. Average Reward
- 1.Average Reward A New Way of Formulating Control Problems.mp4
  
  Preview
- 2.Satinder Singh on Intrinsic Rewards.mp4
  
  Preview
- 3.Week 3 Review.mp4
  
  Preview
Programming Assignment: Function Approximation and Control
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
Quiz
- 1-2.png
  
  Preview
- 3-4.png
  
  Preview
- 5.png
  
  Preview
- 6.png
  
  Preview
- 7.png
  
  Preview
- 8.png
  
  Preview
- 9.png
  
  Preview
- 10.png
  
  Preview
- 11.png
  
  Preview
- 12.png
  
  Preview
1. Learning Parameterized Policies
- 1.Learning Policies Directly.mp4
  
  Preview
- 2.Advantages of Policy Parameterization.mp4
  
  Preview
2. Policy Gradient for Continuing Tasks
- 1.The Objective for Learning Policies.mp4
  
  Preview
- 2.The Policy Gradient Theorem.mp4
  
  Preview
3. Actor-Critic for Continuing Tasks
- 1.Estimating the Policy Gradient.mp4
  
  Preview
- 2.Estimating the Policy Gradient.mp4
  
  Preview
4. Policy Parameterizations
- 1.Actor-Critic with Softmax Policies.mp4
  
  Preview
- 2.Demonstration with Actor-Critic.mp4
  
  Preview
- 3.Gaussian Policies for Continuous Actions.mp4
  
  Preview
- 4.Week 4 Summary.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
5. Course Wrap-up
- Congratulations! Course 4 Preview.mp4
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5-6.png
  
  Preview
- 7-8-9.png
  
  Preview
- 10.png
  
  Preview
- 11-12.png
  
  Preview
1. Course Introduction
- 1.Course 4 Introduction.mp4
  
  Preview
- 2.Meet your instructors!.mp4
  
  Preview
- 8inzzDYkSJ2p88w2JEidAw_8619f632310f4066a6c431a5cef67e12_A-Complete-Reinforcement-Learning-System-Capstone-_-Learning-Objectives.pdf
  
  Preview
1. Final Project: Milestone 1
- 1.Initial Project Meeting with Martha Formalizing the Problem.mp4
  
  Preview
- 2.Andy Barto on What are Eligibility Traces and Why are they so named .mp4
  
  Preview
2. Project Resources
- 1.Lets Review Markov Decision Processes.mp4
  
  Preview
- 2.Lets Review Examples of Episodic and Continuing Tasks.mp4
  
  Preview
Assigment
- Assignment1-v2.ipynb
  
  Preview
- Files.zip
  
  Preview
1. Weekly Learning Goals
- 1.Meeting with Niko Choosing the Learning Algorithm.mp4
  
  Preview
2.Project Resources
- 1.Lets Review Expected Sarsa.mp4
  
  Preview
- 2.Lets Review What is Q-learning .mp4
  
  Preview
- 3.Lets Review Average Reward- A New Way of Formulating Control Problems.mp4
  
  Preview
- 4.Lets Review Actor-Critic Algorithm.mp4
  
  Preview
- 5.Csaba Szepesvari on Problem Landscape.mp4
  
  Preview
- 6.Andy and Rich Advice for Students.mp4
  
  Preview
Quiz
- 1-2-3.png
  
  Preview
- 4-5-6.png
  
  Preview
- 7.png
  
  Preview
- 8.png
  
  Preview
1. Weekly Learning Goals
- 1.Agent Architecture Meeting with Martha Overview of Design Choices.mp4
  
  Preview
2. Project Resources
- 1.Lets Review Non-linear Approximation with Neural Networks.mp4
  
  Preview
- 2.Drew Bagnell on System ID + Optimal Control.mp4
  
  Preview
- 3.Susan Murphy on RL in Mobile Health.mp4
  
  Preview
Quiz
- 1-2.png
  
  Preview
- 3-4-5.png
  
  Preview
- 6-7.png
  
  Preview
- 8-9.png
  
  Preview
- 10.png
  
  Preview
- 11.1.png
  
  Preview
- 11.png
  
  Preview
- 12.png
  
  Preview
1. Weekly Learning Goals
- 1.Meeting with Adam Getting the Agent Details Right.mp4
  
  Preview
2. Project Resources
- 1.Lets Review Optimization Strategies for NNs.mp4
  
  Preview
- 2.Lets Review Expected Sarsa with Function Approximation.mp4
  
  Preview
- 3.Lets Review Dyna & Q-learning in a Simple Maze.mp4
  
  Preview
- 4.Meeting with Martha In-depth on Experience Replay.mp4
  
  Preview
- 5.Martin Riedmiller on The Collect and Infer framework for data-efficient RL.mp4
  
  Preview
Assigment
- Course4ProgrammingAssignment2-v4.ipynb
  
  Preview
- Files.zip
  
  Preview
1. Weekly Learning Goals
- 1.Meeting with Adam Parameter Studies in RL.mp4
  
  Preview
2. Project Resources
- 1.Lets Review Comparing TD and Monte Carlo.mp4
  
  Preview
- 2.Joelle Pineau about RL that Matters.mp4
  
  Preview
Assigment
- assignment.ipynb
  
  Preview
- Files.zip
  
  Preview
3. Congratulations!
- 1.Meeting with Martha Discussing Your Results.mp4
  
  Preview
- 2.Course Wrap-up.mp4
  
  Preview
- 3.Specialization Wrap-up.mp4
  
  Preview