Zobrazeno 1 - 10
of 249
pro vyhledávání: '"Leslie Kaelbling"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 26:1422-1428
This paper presents a theoretical advance by which factored POSGs can be decomposed into local models. We formalize the interface between such local models as the influence agents can exert on one another; and we prove that this interface is sufficie
A longstanding objective in classical planning is to synthesize policies that generalize across multiple problems from the same domain. In this work, we study generalized policy search-based methods with a focus on the score function used to guide th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::020ab1402178793376ff324c44e59188
http://arxiv.org/abs/2204.10420
http://arxiv.org/abs/2204.10420
Autor:
Clement Gehring, Masataro Asai, Rohan Chitnis, Tom Silver, Leslie Kaelbling, Shirin Sohrabi, Michael Katz
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems found in class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3aced596ec4f20d1269d75701dea6145
http://arxiv.org/abs/2109.14830
http://arxiv.org/abs/2109.14830
Publikováno v:
arXiv
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::216ad766c3f6950aa720b7d00fe48c47
https://hdl.handle.net/1721.1/132313
https://hdl.handle.net/1721.1/132313
Autor:
Noel Hollingsworth, Jason Meyer, Ryan McGee, Jeffrey Doering, George Konidaris, Leslie Kaelbling
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 28:2984-2989
We applied a policy search algorithm to the problem of optimizing a start-stop controller—a controller used in a car to turn off the vehicle’s engine, and thus save energy, when the vehicle comes to a temporary halt. We were able to improve the e
Autor:
Truong-Huy Nguyen, David Hsu, Wee-Sun Lee, Tze-Yun Leong, Leslie Kaelbling, Tomas Lozano-Perez, Andrew Grant
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 7:61-66
We apply decision theoretic techniques to construct non-player characters that are able to assist a human player in collaborative games. The method is based on solving Markov decision processes, which can be difficult when the game state is described
Autor:
Thomas Dean, Dana Angluin, Kenneth Basye, Sean Engelson, Leslie Kaelbling, Evangelos Kokkevis, Oded Maron
Publikováno v:
Machine Learning. 18:81-108
Autor:
Núñez-Molina, Carlos1 (AUTHOR) ccaarlos@ugr.es, Mesejo, Pablo1 (AUTHOR) pmesejo@ugr.es, Fernández-Olivares, Juan1 (AUTHOR) faro@decsai.ugr.es
Publikováno v:
ACM Computing Surveys. Nov2024, Vol. 56 Issue 11, p1-36. 36p.
Autor:
Chen, Zhiqian1 (AUTHOR) zchen@cse.msstate.edu, Chen, Fanglan2 (AUTHOR) fanglanc@vt.edu, Zhang, Lei2 (AUTHOR) zhanglei@vt.edu, Ji, Taoran3 (AUTHOR) taoran.ji@tamucc.edu, Fu, Kaiqun4 (AUTHOR) kaiqun.fu@sdstate.edu, Zhao, Liang5 (AUTHOR) liang.zhao@emory.edu, Chen, Feng6 (AUTHOR) feng.chen@utdallas.edu, Wu, Lingfei7 (AUTHOR) lwu@email.wm.edu, Aggarwal, Charu8 (AUTHOR) charu@us.ibm.com, Lu, Chang-Tien2 (AUTHOR) ctlu@vt.edu
Publikováno v:
ACM Computing Surveys. May2024, Vol. 56 Issue 5, p1-42. 42p.
Autor:
Seyyedi, Azra1 (AUTHOR) azra.seyyedi@iasbs.ac.ir, Bohlouli, Mahdi2 (AUTHOR) bohlouli@iasbs.ac.ir, Oskoee, Seyedehsan Nedaaee3 (AUTHOR) nedaaee@iasbs.ac.ir
Publikováno v:
ACM Computing Surveys. May2024, Vol. 56 Issue 5, p1-33. 33p.