- Published on
DevFest SG Talk: Lessons from Reinforcement Learning
- Authors
- Name
- Martin Andrews
- @mdda123
Presentation Link
I was asked to give one of the Machine Learning talks at DevFest Singapore 2025 - a large event, at which I spoke in the Developer Space to a capacity audience.
My talk was titled "Lessons from RL training", and included the following sections:
- Phases of Training (recap)
- Lessons from Reinforcement Learning
- How can we benefit?
- Fine-Tuning & Prompting models
- Wrap-up
Description :
From the Gemini x Singapore Symposium, it became clear how much Base model outputs were valued by Google's top researchers doing Reinforcement Learning. Martin will explain how some of these lessons can be carried over to enabling better Prompting and more efficient Supervised Fine-Tuning techniques.
Many thanks to the Singapore GDG for inviting me!
And the slides for my talk are here :
If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.
