The Deep Reinforcement Learning Nanodegree has four courses: Introduction to Deep Reinforcement Learning, Value-Based Methods, Policy-Based Methods, and Multi-Agent RL. Students learn to implement classical solution methods, define Markov decision processes, policies, and value functions, and derive Bellman equations. They learn dynamic programming, Monte Carlo methods, temporal-difference methods, deep RL, and apply these techniques to solve real-world problems. They learn to train agents to navigate virtual worlds, generate optimal financial trading strategies, and apply RL to multiple interacting agents.
Overview
Syllabus
- Introduction to Deep Reinforcement Learning
- Value Based Methods
- Apply deep learning architectures to reinforcement learning tasks. Train your own agent that navigates a virtual world from sensory data.
- Policy-Based Methods
- Multi-Agent Reinforcement Learning
- Special Topics in Deep Reinforcement Learning
- Neural Networks in PyTorch
- Computing Resources
- C++ Programming
- Career Services
Taught by
Alexis Cook, Arpan Chakraborty, Mat Leonard, Luis Serrano, Cezanne Camacho, Dana Sheahan, Chhavi Yadav, Juan Delgado, Miguel Morales, Bardia H., Ross A., Camilo G., Fabian V., Ho Chit S. and Robson M.
Tags
Related Courses
Related articles
Reviews
5.0 rating, based on 2 Class Central reviews
4.6 rating at Udacity based on 328 ratings
-
"The program is going really well, it has exceeded my expectations! I´ve learned a lot so far and I think this course will help me tackle real world problems in my organization.
Thank you Udacity for your support! " -
Even though is quite tough, especially for someone coming from a different field than computer science, the course is very well structured and the contents are very well explained by the teacher, in addition all material provided (research papers, codes, descriptions and guides) are very helpful. It is exactly what I was looking for
