Abstract
Future advanced AI systems may learn sophisticated strategies through reinforcement learning (RL) that humans cannot understand well enough to safely evaluate. We propose a training method which avoids agents learning undesired multi-step plans that receive high reward even if humans are not able to detect that the behaviour is undesired. The method, Myopic Optimization with Non-myopic Approval (MONA), works by combining short-sighted optimization with far-sighted reward. We demonstrate that MONA can prevent multi-step reward hacking that ordinary RL causes, even without being able to detect the reward hacking and without any extra information that the ordinary RL does not get access to. We study MONA empirically in three settings which model different misalignment failure modes including 2-step environments with LLMs representing delegated oversight and encoded reasoning and longer-horizon gridworld environments representing sensor tampering.
Authors
Sebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah
Venue
arXiv