Paper Reading Group: Human-level control through deep reinforcement learning (Deep Q-Network)

Google's Deep Mind paper Human-level control through deep reinforcement learning was the catalyst in Reinforcement Learning in 2015. Advances from this paper today are used in ChatGPT, robots, video game characters, ad ranking, and much more. The paper has over 25k citations and is published in Nature.

What's in store?

• Discussion on what Reinforcement Learning is
• A discussion of the paper and the Deep Q-Network model discussed in the paper
• Look at how Reinforcement Learning is applied to various domains

You can download the paper from Google Deep Mind's website

Your host:

Sai Shreyas Bhavanasi has published 2 first author papers applying Deep Reinforcement Learning to path planning and is currently working in computer vision research building Image Retrieval models for sparse data applications.