2 papers
cs.AI2016
Self-Modification of Policy and Utility Function in Rational Agents
Tom Everitt, Daniel Filan, Mayank Daswani +1
Any agent that is part of the environment it interacts with and has versatile actuators (such as arms and fingers), will in principle have the ability to self-modify -- for example…
cs.AI2015
A Definition of Happiness for Reinforcement Learning Agents
Mayank Daswani, Jan Leike
What is happiness for reinforcement learning agents? We seek a formal definition satisfying a list of desiderata. Our proposed definition of happiness is the temporal difference er…