JOTB19 - Getting started with Deep Reinforcement Learning by Nicolas Kuhaupt
Reinforcement Learning is a hot topic in Artificial Intelligence (AI) at the moment with the most prominent example of AlphaGo Zero. It shifted the boundaries of what was believed to be possible with AI. In this talk, we will have a look into Reinforcement Learning and its implementation.
Reinforcement Learning is a class of algorithms which trains an agent to act optimally in an environment. The most prominent example is AlphaGo Zero, where the agent is trained to place tokens on the board of Go in order to win the game. AlphaGo Zero has won against the world champion which was thought to be impossible at that time. This was enabled by combining Reinforcement Learning with Deep Neural Networks and is today known as Deep Reinforcement Learning. This has shifted the frontier of Artificial Intelligence and enabled multiple complex use cases, among them controlling the cooling devices in the server rooms by google. Applying Deep Reinforcement Learning saved them several million in power costs. In this talk, we will understand the basics of Deep Reinforcement Learning and implement a simple example. We will have a look at OpenAIs gym which is the defacto standard for Reinforcement Learning environments. This will enable the audience to implement both an environment and Reinforcement Learning agent on their own.
Смотрите видео JOTB19 - Getting started with Deep Reinforcement Learning by Nicolas Kuhaupt онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь J On The Beach 07 Июнь 2019, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 158 раз и оно понравилось 5 людям.