Fee may apply
This course has high demand for enrollment. Please join the wait list, and make sure you submit your NDO application and transcripts to be considered for this enrollment request. A team member from Student Client Services will contact you to confirm your enrollment request if spots become available.
Reinforcement Learning (RL) provides a powerful paradigm for artificial intelligence and the enabling of autonomous systems to learn to make good decisions. RL is relevant to an enormous range of tasks, including robotics, game playing, consumer modeling and healthcare.
This class will provide a solid introduction to the field of RL. Students will learn about the core challenges and approaches in the field, including generalization and exploration.
Through a combination of lectures, and written and coding assignments, students will become well-versed in key ideas and techniques for RL. Assignments will include the basics of reinforcement learning as well as deep reinforcement learning-- an extremely promising new area that combines deep learning techniques with reinforcement learning. In addition, students will advance their understanding and the field of RL through an open-ended project.
PrerequisitesProficiency in Python, CS229 or equivalents or permission of the instructor. Background in linear algebra and basic probability.
- Key features of RL
- Policy iteration, TD learning and Q-learning
- Linear value approximation
- MDP, POMDP, bandit, batch offline and online RL
- RL algorithms
- Open challenges and hot topics in RL
Note on Course Availability
This course is typically offered Winter quarter.
The course schedule is displayed for planning purposes – courses can be modified, changed, or cancelled. Course availability will be considered finalized on the first day of open enrollment. For quarterly enrollment dates, please refer to our graduate certificate homepage.
|Dates:||January 6 - March 13, 2020|
Provides Stanford University credit that may later be applied towards a graduate degree or certificate. Includes access to online course materials and videos for the duration of the academic quarter. Starting Autumn 2016 there is a $100 fee per course for courses dropped before the drop deadline. Click here for more information about our Registration Policies.
NotesEnrollment Dates: October 27 to December 9, 2019
Computer Science Department Requirement
Students taking graduate courses in Computer Science must enroll for the maximum number of units and maintain a B or better in each course in order to continue taking courses under the Non Degree Option.
This course may not currently be available to learners in some states and territories.