Iliad Intensive

Next up

Day 6, Decision Theory and Reinforcement Learning

Fernando Rosas

Next Mon 14 Sep, from 10:00
Where 23 Curtain Road, London EC2A 3LT
Reinforcement learning motivated from preferences: what the von Neumann-Morgenstern axioms assume, how preferences become a utility function, and how that becomes the reward, return and policy vocabulary of a Markov decision process.

Before itpartial orders, expected utility

2026-09-11 · 20 days, 17 modules, 19 teachers and TAs, 54 participants

Airtable read 2026-09-12, 20 rows.