MLSG - Reinforcement Learning : DIY and RSI

About this event

This month, we're going into the latest advances in model training - including Doing It Yourself! Talks: "Cooperation vs Competition" - Martin Andrews People are trying to get models to train more effectively by setting up processes that cause models to compete with each other (for instance AlphaZero), or act cooperatively towards a common goal. Martin will go over some of the history - and look at the latest directions. "LLM RL Training for Beginners" - Sam Witteveen In a this talk, Sam will talk about the different applications of reinforcement learning for LLMs, how you can use them, and how you can get started training Reinforcement Learning on LLMs yourself. FOOD UPDATE : Google has told us that there WILL BE pizza at the event \-\-\- Talks will start at 7:10pm (entry at 6:45pm) and end at around 9:00pm, at which point attendees can come up to the front for a bit of a chat with each other, and the speakers. Due to some recent security incidents at the venue please take note of the new DevSpace security procedures https://bit.ly/devspace-security Attendees will not be admitted later than 15min after the talks have started. As always, we're actively looking for more speakers - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with keras, PyTorch, JAX and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or an enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would love to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Martin at one of the events.