Optimization Issues in KL-Constrained Approximate Policy Iteration. Lazic, N., Hao, B., Abbasi-Yadkori, Y., Schuurmans, D., & Szepesvári, C. CoRR, 2021. Paper bibtex @article{DBLP:journals/corr/abs-2102-06234,
author = {Nevena Lazic and
Botao Hao and
Yasin Abbasi{-}Yadkori and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {Optimization Issues in KL-Constrained Approximate Policy Iteration},
journal = {CoRR},
volume = {abs/2102.06234},
year = {2021},
url = {https://arxiv.org/abs/2102.06234},
archivePrefix = {arXiv},
eprint = {2102.06234},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06234.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Downloads: 0
{"_id":"ohXAXRdds9ePRbBff","bibbaseid":"lazic-hao-abbasiyadkori-schuurmans-szepesvri-optimizationissuesinklconstrainedapproximatepolicyiteration-2021","author_short":["Lazic, N.","Hao, B.","Abbasi-Yadkori, Y.","Schuurmans, D.","Szepesvári, C."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Nevena"],"propositions":[],"lastnames":["Lazic"],"suffixes":[]},{"firstnames":["Botao"],"propositions":[],"lastnames":["Hao"],"suffixes":[]},{"firstnames":["Yasin"],"propositions":[],"lastnames":["Abbasi-Yadkori"],"suffixes":[]},{"firstnames":["Dale"],"propositions":[],"lastnames":["Schuurmans"],"suffixes":[]},{"firstnames":["Csaba"],"propositions":[],"lastnames":["Szepesvári"],"suffixes":[]}],"title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","journal":"CoRR","volume":"abs/2102.06234","year":"2021","url":"https://arxiv.org/abs/2102.06234","archiveprefix":"arXiv","eprint":"2102.06234","timestamp":"Thu, 18 Feb 2021 00:00:00 +0100","biburl":"https://dblp.org/rec/journals/corr/abs-2102-06234.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@article{DBLP:journals/corr/abs-2102-06234,\n author = {Nevena Lazic and\n Botao Hao and\n Yasin Abbasi{-}Yadkori and\n Dale Schuurmans and\n Csaba Szepesv{\\'{a}}ri},\n title = {Optimization Issues in KL-Constrained Approximate Policy Iteration},\n journal = {CoRR},\n volume = {abs/2102.06234},\n year = {2021},\n url = {https://arxiv.org/abs/2102.06234},\n archivePrefix = {arXiv},\n eprint = {2102.06234},\n timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2102-06234.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Lazic, N.","Hao, B.","Abbasi-Yadkori, Y.","Schuurmans, D.","Szepesvári, C."],"key":"DBLP:journals/corr/abs-2102-06234","id":"DBLP:journals/corr/abs-2102-06234","bibbaseid":"lazic-hao-abbasiyadkori-schuurmans-szepesvri-optimizationissuesinklconstrainedapproximatepolicyiteration-2021","role":"author","urls":{"Paper":"https://arxiv.org/abs/2102.06234"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.ualberta.ca/~szepesva/papers/567.bib","dataSources":["cd5AYQRw3RHjTgoQc"],"keywords":[],"search_terms":["optimization","issues","constrained","approximate","policy","iteration","lazic","hao","abbasi-yadkori","schuurmans","szepesvári"],"title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","year":2021}