Deep Reinforcement Learning

NPFL139

Reinforcement learning has been created for situations where the training data does not come in neat pairs question-expected answer. Instead, the reward comes much later, after many steps the system has to make in an environment.

In recent years, reinforcement learning has been combined with deep neural networks, giving rise to game agents with super-human performance (for example for Go, chess, StarCraft II, capable of being trained solely by self-play), datacenter cooling algorithms being 50% more efficient than trained human operators, or faster code for sorting or matrix multiplication. The goal of the course is to introduce reinforcement learning employing deep neural networks, focusing both on the theory and on practical implementations.

Python programming skills and basic PyTorch/TensorFlow skills are required (the latter can be obtained on the Deep Learning course). No previous knowledge of reinforcement learning is necessary.

Details

EXPLORE THE BLOCKS AND COURSES

STILL SOME QUESTIONS?

Contact us at minor@prg.ai and we will get back to you shortly.

Also, don’t forget to follow us on LinkedIn.