About this blog
This are my notes on Reinforcement learning. I got started with David Silver’s lectures on YouTube Then took the four course specilization By Martha nad Adam White from Alberta Coursera. That coverd most of Sutton and Barto’s book. This is a nice course and I got a perfect grade. But I can’t put up the code or quizzes online due to the honor code. - The Deep Reinforcement Learning course by Hugging Face does not have this restrictions. So I’m now working my way theough this.
- Richard S. Sutton has some suggestions like keeping a research notebook. I kept having questions during study and I found that by keeping a notebook I could get some of them out of my head. I could even solve some or make progress.
- The specilization also featured a large number of resaerchers in the field.
- I stated looking them up and seeing if they had interesting talks online.
I started doing that too. The next step is to consolidate the many notes into this blog.
they answers to questions no botherd to ask
This is a space to share my insights about my interests.
Open.AI has a RL blog. They list a bunch of papers on deep RL. I plan to read them and write about them here time premmiting.
However there is lots of intersting material I found online
Talk on double robust tomphson sampling
AdKDD 2022 Dynamic collaborative filtering Thompson Sampling for cross-domain ad recommendation