A Formal Solution to the Grain of Truth Problem. Leike, J, Taylor, J, & Fallenstein, B jan.leike.name.
abstract   bibtex   
Abstract A Bayesian agent acting in a multi-agent environment learns to predict the other agents' policies if its prior assigns positive probability to them (in other words, its prior contains a grain of truth). Finding a reasonably large class of policies that contains the.
@Article{Leike,
author = {Leike, J and Taylor, J and Fallenstein, B}, 
title = {A Formal Solution to the Grain of Truth Problem}, 
journal = {jan.leike.name}, 
volume = {}, 
number = {}, 
pages = {}, 
year = {}, 
abstract = {Abstract A Bayesian agent acting in a multi-agent environment learns to predict the other agents\' policies if its prior assigns positive probability to them (in other words, its prior contains a grain of truth). Finding a reasonably large class of policies that contains the.}, 
location = {}, 
keywords = {}}

Downloads: 0