In this episode, Sanyam Bhutani interviews a researcher, practitioner and open source contributor: Sergey Kolesnikov, creator of catalyst, which is a deep learning and reinforcement learning framework based on Pytorch.
Every year the topic of reinforcement learning (RL) is getting hotter and more hype. And every year, DeepMind and OpenAI add fuel to the fire with a new superhuman performance bot. Is there something really worthwhile behind this? And what are the latest trends in the entire RL variety? Let’s find out!
Deep Learning requires a lot of experiments, models, and hypotheses testing. In this talk, I will tell you about Catalyst.DL - a library for simplifying the development of deep learning solutions.