?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Meta+reinforcement+learning+with+latent+variable+Gaussian+processes&rft.creator=S%C3%A6mundsson%2C+S&rft.creator=Hofmann%2C+K&rft.creator=Deisenroth%2C+MP&rft.description=Learning+from+small+data+sets+is+critical+in+many+practical+applications+where+data+collection+is+time+consuming+or+expensive%2C+e.g.%2C+robotics%2C+animal+experiments+or+drug+design.+Meta+learning+is+one+way+to+increase+the+data+efficiency+of+learning+algorithms+by+generalizing+learned+concepts+from+a+set+of+training+tasks+to+unseen%2C+but+related%2C+tasks.+Often%2C+this+relationship+between+tasks+is+hard+coded+or+relies+in+some+other+way+on+human+expertise.+In+this+paper%2C+we+frame+meta+learning+as+a+hierarchical+latent+variable+model+and+infer+the+relationship+between+tasks+automatically+from+data.+We+apply+our+framework+in+a+modelbased+reinforcement+learning+setting+and+show+that+our+meta-learning+model+effectively+generalizes+to+novel+tasks+by+identifying+how+new+tasks+relate+to+prior+ones+from+minimal+data.+This+results+in+up+to+a+60%25+reduction+in+the+average+interaction+time+needed+to+solve+tasks+compared+to+strong+baselines.&rft.publisher=Association+for+Uncertainty+in+Artificial+Intelligence+(AUAI)&rft.contributor=Elidan%2C+G&rft.contributor=Kersting%2C+K&rft.date=2018-08-06&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A+Elidan%2C+G+and+Kersting%2C+K%2C+(eds.)+Proceedings+of+34th+Conference+on+Uncertainty+in+Artificial+Intelligence+(uai+2018).++(pp.+pp.+642-652).++Association+for+Uncertainty+in+Artificial+Intelligence+(AUAI)%3A+Monterey%2C+CA%2C+USA.+(2018)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10083560%2F1%2FDeisenroth_permitted%2520VoR_235.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10083560%2F&rft.rights=open