Practical Reinforcement Learning
Higher School of Economics
I am very proud that I survived and completed this thorny but exciting journey with Honors. I spent nearly 1 month on this very challenging course, which covers enormous amount of knowledge. The lecture videos are all well-prepared, they not only help me consolidate my original understanding, but also teach me a lot of new things.
There are 13 programming assignments, each of them actually is a tough mini-project. The beauty of them is you are free to use any neural networks and debugging techniques. Make sure you know how to use TensorFlow before getting started.
Besides all fundamental stuff like Bellman equations, Q-learning, SARSA, etc; there are a few topics impressed me a lot. First is Deep Q-Network, I spent quite a few days to debugging my neural network. Then policy-based REINFORCE algorithm and the famous Actor-Critic algorithm. Lastly the advanced exploration techniques and Monte Carlo Tree Search. You will need to complete the implementation of them, very valuable for future reference.
I am Kesler Zhu, thank you for visiting. Checkout all of my course reviews at http://KZHU.ai
All of your support will be used for maintenance of this site and more great content. I am humbled and grateful for your generosity. Thank you!
Don't forget to sign up newsletter, don't miss any chance to learn.
Or share what you've learned with friends!Tweet