Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Harsha Kokel"'
Publikováno v:
Neural Computing and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c83ba7511fc3b9be21eebf119eb3e5f0
https://doi.org/10.1007/s00521-022-08119-y
https://doi.org/10.1007/s00521-022-08119-y
Autor:
Harsha Kokel, Nikhilesh Prabhakar, Balaraman Ravindran, Erik Blasch, Prasad Tadepalli, Sriraam Natarajan
Publikováno v:
2022 25th International Conference on Information Fusion (FUSION).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::461c857099a8bf1c768dc3fa871e9510
https://doi.org/10.23919/fusion49751.2022.9841246
https://doi.org/10.23919/fusion49751.2022.9841246
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 31:533-541
State abstraction is necessary for better task transfer in complex reinforcement learning environments. Inspired by the benefit of state abstraction in MAXQ and building upon hybrid planner-RL architectures, we propose RePReL, a hierarchical framewor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed7882990f8420c3bce61acf721d5686
https://doi.org/10.1609/icaps.v31i1.16001
https://doi.org/10.1609/icaps.v31i1.16001
Publikováno v:
AAAI
Incorporating richer human inputs including qualitative constraints such as monotonic and synergistic influences has long been adapted inside AI. Inspired by this, we consider the problem of using such influence statements in the successful gradient-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a0f67decc716125024142ee676803f7
https://doi.org/10.1609/aaai.v34i04.5873
https://doi.org/10.1609/aaai.v34i04.5873
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:12989-12990
While AI planning and Reinforcement Learning (RL) solve sequential decision-making problems, they are based on different formalisms, which leads to a significant difference in their action spaces. When solving planning problems using RL algorithms, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::baedf1c0df27f2d46d99a49a29f973fe
https://doi.org/10.1609/aaai.v36i11.21631
https://doi.org/10.1609/aaai.v36i11.21631
Autor:
Sriraam Natarajan, Athresh Karanam, Alexander Hayes, Predrag Radivojac, David M. Haas, Harsha Kokel
Publikováno v:
Artificial Intelligence in Medicine ISBN: 9783030772109
AIME
Artif Intell Med Conf Artif Intell Med (2005-)
AIME
Artif Intell Med Conf Artif Intell Med (2005-)
Qualitative influence statements are often provided a priori to guide learning; we answer a challenging reverse task and automatically extract them from a learned probabilistic model. We apply our Qualitative Knowledge Extraction method toward early
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80f77dccd95f867197a2a428bed1b4c1
https://doi.org/10.1007/978-3-030-77211-6_59
https://doi.org/10.1007/978-3-030-77211-6_59
Publikováno v:
FIRE
The Morpheme Extraction task (MET) was organized for the first time in FIRE 2012 and subsequently in FIRE 2013. Participating systems were required to provide morphemes of given term lists. The track was offered in five languages viz. Bengali, Gujara
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96472bb4d5892cc99dca7c495cb2a3f7
https://doi.org/10.1145/2701336.2701637
https://doi.org/10.1145/2701336.2701637