Course Summary
This course is designed to teach the practical aspects of reinforcement learning, including deep reinforcement learning techniques. Students will learn about the latest algorithms and methods for building real-world applications.Key Learning Points
- Learn how to apply reinforcement learning to practical problems
- Understand the latest deep reinforcement learning techniques
- Gain experience building real-world applications
Related Topics for further study
Learning Outcomes
- Apply reinforcement learning to practical problems
- Implement deep reinforcement learning techniques
- Build real-world applications
Prerequisites or good to have knowledge before taking this course
- Basic understanding of calculus, linear algebra, and probability
- Proficiency in Python programming
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
- Video lectures
- Assignments and quizzes
Similar Courses
- Applied AI with DeepLearning
- Advanced Machine Learning Specialization
- Applied Data Science with Python Specialization
Related Education Paths
- Master of Computer Science in Artificial Intelligence at Georgia Tech
- Master of Science in Computer Science with a Concentration in Artificial Intelligence at Stanford University
Related Books
Description
Welcome to the Reinforcement Learning course.
Outline
- Intro: why should I care?
- About the University
- Why should you care
- Reinforcement learning vs all
- Multi-armed bandit
- Decision process & applications
- Markov Decision Process
- Crossentropy method
- Approximate crossentropy method
- More on approximate crossentropy method
- Evolution strategies: core idea
- Evolution strategies: math problems
- Evolution strategies: log-derivative trick
- Evolution strategies: duct tape
- Blackbox optimization: drawbacks
- About University
- Rules on the academic integrity in the course
- FAQ
- Primers
- About honors track
- Extras
- At the heart of RL: Dynamic Programming
- Reward design
- State and Action Value Functions
- Measuring Policy Optimality
- Policy: evaluation & improvement
- Policy and value iteration
- Optional: Reward discounting from a mathematical perspective
- External links: Reward Design
- Discrete Stochastic Dynamic Programming
- Reward design
- Optimality in RL
- Policy Iteration
- Model-free methods
- Model-based vs model-free
- Monte-Carlo & Temporal Difference; Q-learning
- Exploration vs Exploitation
- Footnote: Monte-Carlo vs Temporal Difference
- Accounting for exploration. Expected Value SARSA
- On-policy vs off-policy; Experience replay
- Extras
- Model-free reinforcement learning
- Approximate Value Based Methods
- Supervised & Reinforcement Learning
- Loss functions in value based RL
- Difficulties with Approximate Methods
- DQN – bird's eye view
- DQN – the internals
- DQN: statistical issues
- Double Q-learning
- More DQN tricks
- Partial observability
- TD vs MC
- Extras
- DQN follow-ups
- MC & TD
- SARSA and Q-learning
- DQN
- Policy-based methods
- Intuition
- All Kinds of Policies
- Policy gradient formalism
- The log-derivative trick
- REINFORCE
- Advantage actor-critic
- Duct tape zone
- Policy-based vs Value-based
- Case study: A3C
- Combining supervised & reinforcement learning
- Stability of policy-based vs value-based methods
- Extras
- A policy-based quiz
- Exploration
- Recap: bandits
- Regret: measuring the quality of exploration
- The message just repeats. 'Regret, Regret, Regret.'
- Intuitive explanation
- Thompson Sampling
- Optimism in face of uncertainty
- UCB-1
- Bayesian UCB
- Introduction to planning
- Monte Carlo Tree Search
- Extras: exploration
- Extras: Planning
- Materials
- Outro
- Exploration
- MCTS
Summary of User Reviews
Discover the practical aspects of Reinforcement Learning in this course on Coursera. Students have given positive reviews of this course, praising its hands-on approach to learning.Key Aspect Users Liked About This Course
The hands-on approach to learning was praised by many users.Pros from User Reviews
- Provides practical knowledge of Reinforcement Learning
- Hands-on approach to learning
- Good balance of theory and application
- Instructors are knowledgeable and engaging
- Course materials are well-organized and easy to follow
Cons from User Reviews
- Requires prior knowledge of Python programming
- Some users found the course to be challenging
- Limited discussion of deep reinforcement learning
- Some users found the course to be too theoretical
- Lacks practical advice for applying RL in real-world situations
Pavel Shvechikov
4.3 Raiting
Machine Learning, Data Science and Deep Learning with Python
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Complete hands-on machine learning tutorial with data science, Tensorflow, artificial intelligence, and neural networks New! Updated for 2021 with extra content on generative models: variational auto-encoders (VAE's) and generative adversarial models (GAN's)...
Deep Learning with Python - Novice to Pro!
- 3.8
-
![]()
![]()
![]()
![]()
![]()
Practical recipes on Neural Network modeling, Reinforcement & Transfer Learning using Python's Deep Learning tools Deep Learning is revolutionizing a wide range of industries....
Data Science: Supervised Machine Learning in Python
- 4.8
-
![]()
![]()
![]()
![]()
![]()
Full Guide to Implementing Classic Machine Learning Algorithms in Python and with Scikit-Learn In recent years, we've seen a resurgence in AI, or artificial intelligence, and machine learning....
Reinforcement Learning for Trading Strategies
- 3.7
-
![]()
![]()
![]()
![]()
![]()
In the final course from the Machine Learning for Trading specialization, you will be introduced to reinforcement learning (RL) and the benefits of using reinforcement learning in trading strategies....
