Deep Reinforcement Learning

Teacher

admin

Level

Advanced

Prerequisites

[same as CV and NLP] Advanced Program. Intermediate/Advanced Python – can write nested for loops and can read and understand code written by others. intermediate statistics and probability.
Intermediate Machine Learning – can describe backpropagation and have seen examples of neural network architecture, eg. a CNN. Familiarity with deep learning framework like TensorFlow, Keras, or PyTorch.

Course Duration

4 months

Udacity current price ( USD)

1356

Reseller price (USD)

1000

Career Focus

This program is designed to build on your existing skills in machine learning and deep learning. As such, it doesn’t prepare you for a specific job, but instead expands your skills in the deep reinforcement learning domain. These skills can be applied to various applications such as gaming, robotics, recommendation systems, autonomous vehicles, financial trading, and more.

Target Audience

students looking to go deep into a specialized AI field. already have experience in the field (even if not actually an AI engineer)

General Curriculum)

Advanced Deep Learning algorithms. Deep Q-Networks, Deep Deterministic Policy Gradients. Train agents that navigates a world with sensory data. Train robotic arms with own algorithm to reach target locations. apply reinforcement learning with multiple, interacting agents. Uses _____ (tools / technology)

Why Take This ND?

N/A

Tools

What They Need: Need a computer on which all of these programs can be installed
What They Will Use/Learn: Python, PyTorch (library in Python), Jupyter Notebook, NumPy, Anaconda, Panda

Projects

- Navigation in a Virtual World
- Continuous Control – train a robitc arm to reach target locations and train a four-legged virtual creature to walk
- Collaboration and Competition – train a pair of agents to play tennis and then soccer