Policy Shaping: Integrating Human Feedback with Reinforcement Learning. Griffith, S., Subramanian, K., Scholz, J., Jr., C. L. I., & Thomaz, A. L. In Burges, C. J. C., Bottou, L., Ghahramani, Z., & Weinberger, K. Q., editors, Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, pages 2625–2633, 2013.
Paper bibtex @inproceedings{DBLP:conf/nips/GriffithSSIT13,
author = {Shane Griffith and
Kaushik Subramanian and
Jonathan Scholz and
Charles L. Isbell Jr. and
Andrea Lockerd Thomaz},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Policy Shaping: Integrating Human Feedback with Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {2625--2633},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/e034fb6b66aacc1d48f445ddfb08da98-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GriffithSSIT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Downloads: 0
{"_id":"CCvgZNyRApC2Dkx3o","bibbaseid":"griffith-subramanian-scholz-jr-thomaz-policyshapingintegratinghumanfeedbackwithreinforcementlearning-2013","author_short":["Griffith, S.","Subramanian, K.","Scholz, J.","Jr., C. L. I.","Thomaz, A. L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Shane"],"propositions":[],"lastnames":["Griffith"],"suffixes":[]},{"firstnames":["Kaushik"],"propositions":[],"lastnames":["Subramanian"],"suffixes":[]},{"firstnames":["Jonathan"],"propositions":[],"lastnames":["Scholz"],"suffixes":[]},{"firstnames":["Charles","L.","Isbell"],"propositions":[],"lastnames":["Jr."],"suffixes":[]},{"firstnames":["Andrea","Lockerd"],"propositions":[],"lastnames":["Thomaz"],"suffixes":[]}],"editor":[{"firstnames":["Christopher","J.","C."],"propositions":[],"lastnames":["Burges"],"suffixes":[]},{"firstnames":["Léon"],"propositions":[],"lastnames":["Bottou"],"suffixes":[]},{"firstnames":["Zoubin"],"propositions":[],"lastnames":["Ghahramani"],"suffixes":[]},{"firstnames":["Kilian","Q."],"propositions":[],"lastnames":["Weinberger"],"suffixes":[]}],"title":"Policy Shaping: Integrating Human Feedback with Reinforcement Learning","booktitle":"Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States","pages":"2625–2633","year":"2013","url":"https://proceedings.neurips.cc/paper/2013/hash/e034fb6b66aacc1d48f445ddfb08da98-Abstract.html","timestamp":"Thu, 21 Jan 2021 00:00:00 +0100","biburl":"https://dblp.org/rec/conf/nips/GriffithSSIT13.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@inproceedings{DBLP:conf/nips/GriffithSSIT13,\n author = {Shane Griffith and\n Kaushik Subramanian and\n Jonathan Scholz and\n Charles L. Isbell Jr. and\n Andrea Lockerd Thomaz},\n editor = {Christopher J. C. Burges and\n L{\\'{e}}on Bottou and\n Zoubin Ghahramani and\n Kilian Q. Weinberger},\n title = {Policy Shaping: Integrating Human Feedback with Reinforcement Learning},\n booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual\n Conference on Neural Information Processing Systems 2013. Proceedings\n of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},\n pages = {2625--2633},\n year = {2013},\n url = {https://proceedings.neurips.cc/paper/2013/hash/e034fb6b66aacc1d48f445ddfb08da98-Abstract.html},\n timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},\n biburl = {https://dblp.org/rec/conf/nips/GriffithSSIT13.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Griffith, S.","Subramanian, K.","Scholz, J.","Jr., C. L. I.","Thomaz, A. L."],"editor_short":["Burges, C. J. C.","Bottou, L.","Ghahramani, Z.","Weinberger, K. Q."],"key":"DBLP:conf/nips/GriffithSSIT13","id":"DBLP:conf/nips/GriffithSSIT13","bibbaseid":"griffith-subramanian-scholz-jr-thomaz-policyshapingintegratinghumanfeedbackwithreinforcementlearning-2013","role":"author","urls":{"Paper":"https://proceedings.neurips.cc/paper/2013/hash/e034fb6b66aacc1d48f445ddfb08da98-Abstract.html"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://dblp.org/pid/i/LCIsbell.bib","dataSources":["j3pAbHEfa852RHtjF"],"keywords":[],"search_terms":["policy","shaping","integrating","human","feedback","reinforcement","learning","griffith","subramanian","scholz","jr.","thomaz"],"title":"Policy Shaping: Integrating Human Feedback with Reinforcement Learning","year":2013}