Wider ML

Machine Learning papers on Arxiv

Authors and titles for recent submissions
http://arxiv.org/list/stat.ML/recent

Avoiding Wireheading with Value Reinforcement Learning∗ Tom Everitt Marcus Hutter Abstract How can we design good goals for arbitrarily intelligent agents? Reinforcement learning (RL) is a natural approach. Unfortunately, RL does not work well for generally intelligent agents, as RL agents are incentivised to shortcut the reward sensor for maximum reward – the so-called wireheading problem. In this paper we suggest an alternative to RL called value reinforcement learning (VRL). In VRL, agents use the reward signal to learn a utility function. The VRL setup allows us to remove the incentive to wirehead by placing a constraint on the agent’s actions. The constraint is defined in terms of the agent’s belief distributions, and does not require an explicit specification of which actions constitute wireheading. Keywords AI safety, wireheading, self-delusion, value learning, reinforcement learning, artificial general intelligence
http://arxiv.org/pdf/1605.03143v1.pdf