Alpha Go Zero left us with our jaws dropped. The Dota2 agent did so even more. And watching the output of companies like DeepMind leaves us stunned in awe. But how do all these systems work? What is this "deep reinforcement learning" magic?
In this session we will first learn the core ideas of reinforcement learning - a bit of math (not too much, promised!), algorithms, learning strategies and more. Then we will see how to implement a reinforcement learning agent in practice. After that we will extend the approach to deep reinforcement learning by adding deep neural networks. To complete the picture, we will have a look at the current software and service ecosystem.
After the session, we will not have built the next Alpha Go Zero, but you will have an idea how you could ... ;)
The agile hype is over. DevOps took over, driven by the need to holistically speed up the IT value chain without paying the bill in production. At the same time, the second wave of digitization is rolling, turning IT systems into an essential ingredient of our business models.
In this context, good architectural work is crucial. But what we often see, is a perfect confusion without a clear direction:
We see architectures ranging from the BDUF over hype-driven and one-size-fits-all architecture to dogmatic pseudo-agile "no architecture".
Yet, we know that architecture is about those decisions that really hurt if you get them wrong. But how can we minimize the risk of getting hurt, especially if we need to go fast? Which approach is right?
In this workshop we will first discuss the challenges of architectural work in a post-agile IT world. Then, we will set up a surprisingly simple down-to-earth approach for modern architectural work. After that we will start to fill the blocks of the framework one by one - with a bit of theory, lots of interaction and hands-on, including discussion, tips, tricks and pitfalls.
After this workshop, we will not have created a silver bullet. But you will have a lot better understanding what architectural work today actually is about, what is important, what is not and how to implement it in practice.