Regret Bounds for Reinforcement Learning with Policy Advice

Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill. Regret Bounds for Reinforcement Learning with Policy Advice. In Hendrik Blockeel, Kristian Kersting, Siegfried Nijssen, Filip Zelezný, editors, Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part I. Volume 8188 of Lecture Notes in Computer Science, pages 97-112, Springer, 2013. [doi]

Authors

Mohammad Gheshlaghi Azar

This author has not been identified. Look up 'Mohammad Gheshlaghi Azar' in Google

Alessandro Lazaric

This author has not been identified. Look up 'Alessandro Lazaric' in Google

Emma Brunskill

This author has not been identified. Look up 'Emma Brunskill' in Google