Conservative Agency via Attainable Utility Preservation

Abstract

Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change the state of its environment. If that change precludes optimization of the correctly specified reward function, then correction is futile. For example, a robotic factory assistant could break expensive equipment due to a reward misspecification; even if the designers immediately correct the reward function, the damage is done. To mitigate this risk, we introduce an approach that balances optimization of the primary reward function with preservation of the ability to optimize auxiliary reward functions. Surprisingly, even when the auxiliary reward functions are randomly generated and therefore uninformative about the correctly specified reward function, this approach induces conservative, effective behavior.

arXiv commentPublished in AI, Ethics, and Society 2020

References in corpus (8)

• Deep reinforcement learning from human preferences
• Cooperative Inverse Reinforcement Learning
• Safe Model-based Reinforcement Learning with Stability Guarantees
• Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
• Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
• A Lyapunov-based Approach to Safe Reinforcement Learning
• Safe Exploration in Markov Decision Processes
• Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning