Search courses 👉
Professional Course

Reinforcement Learning - from Fundamentals to Deep RL

Length
30 hours
Price
750 EUR + tax
Next course start
Start Anytime! See details
Delivery
Self-paced Online
Length
30 hours
Price
750 EUR + tax
Next course start
Start Anytime! See details
Delivery
Self-paced Online
This provider usually responds within 48 hours 👍

Course description

Reinforcement Learning - From Fundamentals to Deep RL is an extensive course designed to provide a comprehensive understanding of reinforcement learning, from its theoretical foundations to the latest advancements in deep reinforcement learning. This course is ideal for graduate-level students, data scientists, AI researchers, and professionals looking to expand their knowledge and apply RL in various domains.

The course begins with a solid background in essential mathematical concepts, including linear algebra, calculus, and probability theory, ensuring you have the necessary tools to tackle more advanced topics. You’ll gain a deep understanding of random variables, density functions, expectation, and probabilities, setting a strong foundation for the rest of the course.

Next, you’ll explore the core concepts of reinforcement learning, including Markov Decision Processes (MDPs), dynamic programming, and key algorithms like Q-learning, Sarsa, and Actor-Critic. You’ll learn the differences between model-based and model-free approaches and how to implement these techniques in both deterministic and stochastic environments. This section of the course includes extensive examples and hands-on practice to reinforce your understanding.

In the deep reinforcement learning section, you’ll delve into advanced topics such as nonlinear function approximation, breakthroughs from DeepMind, and cutting-edge technologies like memory, attention, recurrence, and hierarchical learning. You’ll also explore practical applications of deep RL in trading, speech understanding, load balancing, and more.

The course concludes with a focus on practical tools and implementations. You’ll work with PyTorch and TensorFlow to implement RL algorithms from scratch, use Ray and RLlib for scalable reinforcement learning applications, and learn how to visualize and explain RL models using advanced techniques like TSNE.

With a balanced approach between theory (24.5 hours) and practice (14.5 hours), this course ensures you not only understand the concepts but also gain the hands-on experience needed to apply RL in real-world scenarios.

By the end of this course, participants will:

  • Understand the mathematical foundations required for reinforcement learning.
  • Master core RL concepts, including Markov Decision Processes, policy evaluation, and key algorithms like Q-learning and Actor-Critic.
  • Implement deep reinforcement learning techniques and explore the latest advancements in the field.
  • Apply RL in practical domains such as trading, speech understanding, and load balancing.
  • Use tools like PyTorch, TensorFlow, Ray, and RLlib to build and deploy RL models at scale.

This course offers a comprehensive mix of theory and practice, providing a deep dive into reinforcement learning and its applications. Through a series of practical exercises, you’ll gain the skills and experience needed to implement RL models and apply them in real-world projects.

Upcoming start dates

1 start date available

Start Anytime!

  • Self-paced Online
  • Online
  • English

Who should attend?

Prerequisites

Required:

  • Graduate level of calculus, probability theory, discrete mathematics
  • Basic knowledge of machine learning
  • Ability to understand Python code

Training content

Part I. Background (5h30m)

1. Linear algebra (30m)

a. Overview of concepts

2. Calculus (1h)

a. Integration

b. Derivation

c. Examples

3. Probabilities (4h)
a. Random variables

b. Density functions

c. Expectation

d. Conditional, joint and marginal probabilities

e. Examples
f. Practice

Part II. Overview (11h)

1. RL Introduction (4h)

a. Markov Decision Processes

b. Dynamic programming with example

c. Bellman equation

d. Policy evaluation

e. Policy Iteration

f. Value Iteration

g. Examples

h. Practice
2. Model-based vs model-free (3h)

a. Learning and planning

b. Deterministic

c. Stochastic
d. Linear value-function approximation
e. Comparison and practice
3. Algorithms (4h)
a. Q-learning
b. Sarsa
c. Actor-critic
d. Policy gradient
e. Monte-Carlo tree methods

f. Exploration vs exploitation

e. Examples
g. Practice

Part III. RL + Deep Learning (6h30m)

1. Deep Reinforcement Learning
a. Nonlinear function approximation
b. The DeepMind breaktrough
c. Alpha-Star Explained
2. Latest technologies in DRL (3h)
a. Memory, Attention, Recurrence
b. Inverse RL
c. Multi-agent

d. Hierarchical
e. Evolved rewards – AutoRL

f. Policy optimization

3. Applications and use (2h):

a. Trading
b. Speech understanding and question answering (optional)
c. Load balancing (optional)
d. Other uses (optional)
Part IV. Practical examples and tools (7h)

1. Pytorch / Tensorflow (2h)
a. Tensor basics
b. Implementing a RL algorithm from scratch
c. Testing and visualizing

d. Practice

2. Ray + RLlib (3h30)

a. Main concepts: actors, futures, memory sharing, etc.
b. Worked example
c. Different algorithms
d. Grid search and visualization
e. Practice

3. Visualization and explainability (1h30)

a. SMDP, AMDP, SAMDP

b. Projection to 3D-space with TSNE

c. Examples

Certification / Credits

Objectives

Upon completion of the "Reinforcement Learning - From Fundamentals to Deep RL" course, trainees will be able to:

  • Grasp the fundamental mathematical concepts necessary for reinforcement learning.
  • Apply core RL algorithms and techniques in both deterministic and stochastic environments.
  • Explore and implement advanced deep reinforcement learning models and technologies.
  • Utilize modern tools and frameworks like PyTorch, TensorFlow, and Ray to develop and deploy scalable RL solutions.
  • Visualize and explain RL models using advanced techniques to ensure interpretability and transparency.

Quick stats about Luxoft Training Center?

More than 200 training courses

Conducted over 1,500 training sessions

Customized training solutions for business

Contact this provider

Contact course provider

Fill out your details to find out more about Reinforcement Learning - from Fundamentals to Deep RL.

  Contact the provider

  Get more information

  Register your interest

Country *

reCAPTCHA logo This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Luxoft Training Center
Warsaw Spire, plac Europejski 1
00-844 Warsaw

Luxoft Training Center

Luxoft Training Center — an essential part of the global technology leader, Luxoft, a DXC Technology Company. We play a pivotal role in propelling B2B businesses forward by delivering customized training solutions. Emphasizing the significance of learning and employee development,...

Read more and show all training delivered by this supplier

Ads