UPDATE:

All the code and installation instructions have been updated and verified to work with Pytorch 1.6 !!

Artificial Intelligenceis dynamicallyedging its wayinto our lives. It is alreadybroadly available andwe use it - sometimes evennot knowing it -on daily basis. Soon it will be our permanent, every daycompanion.

And wherecan we place ReinforcementLearning in AIworld? Definitelythis is one of the most promising and fastest growing technologies that can eventuallylead us to General Artificial Intelligence! We can see multiple examples where AIcan achieve amazing results - from reachingsuper human level whileplaying gamestosolvingreal life problems (robotics, healthcare, etc).

Without a doubtit's worth to knowand understandit!

And that's why this course has been created.

We will go through multiple topics, focusing on most important and practical details.We will start from very basic information, graduallybuilding our understanding, and finallyreaching the point wherewe will make our agent learn in human-like way - only from video input!

What's important - of courseweneed to cover some theory - but we will mainly focus on practical part. Goal isto understand WHYand HOW.

In order to evaluate our algorithms we willuseenvironments from - very popular -OpenAIGym. We will start from basic text games, through more complex ones, up to challenging Atari games

Whatwill be covered during the course ?

- Introduction to Reinforcement Learning

- Markov Decision Process

- Deterministic and stochastic environments

- Bellman Equation

- Q Learning

- Exploration vs Exploitation

- Scaling up

- Neural Networks as function approximators

- Deep Reinforcement Learning

- DQN

- Improvements to DQN

- Learning from video input

- Reproducing some of most popular RL solutions

- Tuning parameters and general recommendations

See you in theclass!