Reinforcement Learning with Databricks
In this course, students learn about Reinforcement Learning (RL) paradigm and get hands-on experience on developing/coding RL algorithms.
Reinforcement Learning (RL) is an area of machine learning concerned with agents (algorithms) taking actions in an environment in order to maximize some notion of cumulative reward. RL is the one of three machine learning paradigms, alongside supervised learning and unsupervised learning. In this course, students will learn what Reinforcement Learning is, how to formulate such a problem and how to implement different RL algorithms.
Upon completion of the course, students should be able to:
Formulate a Reinforcement Learning problem
Understand the difference between Supervised, Unsupervised, and Reinforcement Learning
Understand Markov Decision Processes (MDPs)
Understand Dynamic programming
Understand and implement Policy evaluation, Policy Iteration, and Value Iteration algorithms
Understand and implement Model-Free Prediction and Control algorithms such as first-visit Monte Carlo, Temporal Difference and SARSA.
- Intermediate experience with Python programming
- Intermediate experience with Numpy and Pandas
- Intermediate experience with Machine Learning
- Intermediate level knowledge of Probability Theory
- Intermediate level knowledge of Linear Algebra
- The appropriate, web-based programming environment will be provided to students
- This class is taught in Python only