Overview
What you will learn
Through interactive lectures and hands-on exercises, you will:
- understand the difference between supervised learning and RL;
- be able to gauge which problems in your organization can be solved using RL;
- gain a solid understanding of state-of-the-art Deep RL algorithms;
- ability to cast your favorite challenge into the RL framework and recognize the promise and limitations of RL through a hands-on-session and live RL clinic;
- be able to reason about which RL algorithm is most appropriate for the problem at hand.
The Reinforcement Learning course offered by Massachusetts Institute of Technology (MIT) includes the unique opportunity to present your organization’s specific technological challenges to MIT faculty during a live RL Clinic—a session designed to help you identify if RL can be used to solve your problems, determine which approach will be most effective, and design RL applications to resolve the issue. During this process, you will draw on the expertise of the course teaching team, which is comprised of recognized industry experts with experience working at 12 firms across multiple industries, from both startups and big tech.
Programme Structure
The program focuses on:
- Learn when supervised learning is sufficient and when RL can provide a big advantage.
- Learn about Bandits, Contextual Bandits and the more general RL formulation.
- Understand the theory and the practical aspects of how to use popular Deep RL algorithms such as DQN, A3C, PPO, SAC, TD3, MCTS.
- Walk through application of RL algorithms and what made them work.
- Develop rules-of-thumb to reason about when to use which Deep RL Algorithm.
- Understand how to structure the observation, action space and the reward function for optimally training the RL agent.
- Learn about the limitations of Deep RL algorithm, how to tune hyperparameters and practical tricks.
Key information
Duration
- Full-time
- 3 days
Start dates & application deadlines
- Starting
- Apply before
-
Language
Credits
Delivered
Disciplines
Artificial Intelligence Machine Learning View 157 other Short Courses in Artificial Intelligence in United StatesAcademic requirements
We are not aware of any specific GRE, GMAT or GPA grading score requirements for this programme.
English requirements
We are not aware of any English requirements for this programme.
Student insurance
Make sure to cover your health, travel, and stay while studying abroad. Even global coverages can miss important items, so make sure your student insurance ticks all the following:
- Additional medical costs (i.e. dental)
- Repatriation, if something happens to you or your family
- Liability
- Home contents and baggage
- Accidents
- Legal aid
We partnered with Aon to provide you with the best affordable student insurance, for a carefree experience away from home.
Get your student insurance nowStarting from €0.53/day, free cancellation any time.
Remember, countries and universities may have specific insurance requirements. To learn more about how student insurance work at Massachusetts Institute of Technology (MIT) and/or in United States, please visit Student Insurance Portal.
Other requirements
General requirements
- To be able to take full advantage of this program, we recommend that participants have a mathematical background in linear algebra and probability, basic knowledge of deep-learning, and experience with programming (preferably Python).
- This background will help participants follow some of the practical examples more effectively.
- There are two optional assignments in the program that will require a computer with Google CoLab that runs on any browser or Unix/Linux Terminal.
Tuition Fee
-
International
3600 USD/fullTuition FeeBased on the tuition of 3600 USD for the full programme during 3 days. -
National
3600 USD/fullTuition FeeBased on the tuition of 3600 USD for the full programme during 3 days.
Living costs for Boston
The living costs include the total expenses per month, covering accommodation, public transportation, utilities (electricity, internet), books and groceries.