Vai al contenuto
AI.info

events

MLSG - Reinforcement Learning : DIY and RSI

Machine Learning Singapore ospita due interventi sull’apprendimento per rinforzo: competizione contro cooperazione nell’addestramento dei modelli e come iniziare ad addestrare gli LLM con…

MLSG - Reinforcement Learning : DIY and RSI | Eventi sull’IA

In inglese

Starts
2026-10-29 10:45 UTC
Organizer
Machine Learning Singapore
Location
Google Developers Space, Singapore, 80 Pasir Panjang Rd, Singapore, Singapore

A monthly evening held by Machine Learning Singapore, with two talks on reinforcement learning and model training. Martin Andrews covers the history of setting models to compete, as in AlphaZero, or to cooperate toward a shared goal, and where that work is heading; Sam Witteveen explains applications of reinforcement learning for LLMs and how to start training RL on LLMs directly. Talks run from 7:10pm to about 9:00pm, followed by informal conversation with speakers. The group also invites long-form and lightning talk proposals on keras, PyTorch, JAX or deep learning.

Event website