This is a link post.by Michael K. Cohen, Marcus Hutter, Yoshua Bengio, Stuart Russell
Abstract:
In reinforcement learning, if the agent's reward differs from the designers' true utility, even only rarely, the state distribution resulting from the agent's policy can be very bad, in theory and in practice. When RL policies would devolve into undesired behavior, a common countermeasure is KL regularization to a trusted policy ("Don't do anything I wouldn't do"). All current cutting-edge language models are RL agents that are KL-regularized to a "base policy" that is purely predictive. Unfortunately, we demonstrate that when this base policy is a Bayesian predictive model of a trusted policy, the KL constraint is no longer reliable for controlling the behavior of an advanced RL agent. We demonstrate this theoretically using algorithmic information theory, and while systems today are too weak to exhibit this theorized failure precisely, we RL-finetune a language [...]
First published:
December 7th, 2024
Source:
https://www.lesswrong.com/posts/tMrf4Bw27wPT3CaYr/rl-but-don-t-do-anything-i-wouldn-t-do)
---
Narrated by TYPE III AUDIO).
