Zobrazeno 1 - 10
of 17
pro vyhledávání: '"James MacGlashan"'
Autor:
Franziska Eckert, James MacGlashan, Kenta Kawamoto, Michael Spranger, Hiroaki Kitano, Varun Raj Kompella, Michael Thomure, Craig Sherstan, Leilani Gilpin, Rory Douglas, Takuma Seno, Peter R. Wurman, Florian Fuchs, Peter Stone, Roberto Capobianco, Houmehr Aghabozorgi, Alisa Devlic, Peter Durr, Dion Whitehead, Samuel Barrett, Leon Barrett, Patrick MacAlpine, HaoChih Lin, Piyush Khandelwal, Kaushik Subramanian, Declan Oller, Tom Walsh
The authors have requested that this preprint be removed from Research Square.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe59ead6e8492a51c892c659cb391aa5
https://doi.org/10.21203/rs.3.rs-795954/v1
https://doi.org/10.21203/rs.3.rs-795954/v1
Autor:
Peter R. Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas J. Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, HaoChih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano
Publikováno v:
Nature. 602(7896)
Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c424f55a6bc1400dc9a77f034e414c5f
https://pubmed.ncbi.nlm.nih.gov/35140381
https://pubmed.ncbi.nlm.nih.gov/35140381
Publikováno v:
ICRA
It has been recently demonstrated that Temporal Convolution Networks (TCNs) provide state-of-the-art results in many problem domains where the input data is a time-series. TCNs typically incorporate information from a long history of inputs (the rece
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40845029f9bf1daf2c28529fb93143e9
https://doi.org/10.1109/icra48506.2021.9560784
https://doi.org/10.1109/icra48506.2021.9560784
Autor:
Matthew D. Taylor, David L. Roberts, Michael L. Littman, Bei Peng, James MacGlashan, Robert Loftin
Publikováno v:
IEEE Transactions on Emerging Topics in Computational Intelligence. 2:268-277
Existing work in machine learning has shown that algorithms can benefit from the use of curricula—learning first on simple examples before moving to more difficult problems. This work studies the curriculum-design problem in the context of sequenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c4e610a0e5f7bbb679676b0e64501e7
https://doi.org/10.1109/tetci.2018.2829980
https://doi.org/10.1109/tetci.2018.2829980
Publikováno v:
Cognition. 167:91-106
Humans often attempt to influence one another’s behavior using rewards and punishments. How does this work? Psychologists have often assumed that “evaluative feedback” influences behavior via standard learning mechanisms that learn from environ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bacd927292b8fb29be762e1e7cb607cc
https://doi.org/10.1016/j.cognition.2017.03.006
https://doi.org/10.1016/j.cognition.2017.03.006
Autor:
Nakul Gopalan, Marie DesJardins, Michael Littman, James MacGlashan, Shawn Squire, Stefanie Tellex, John Winder, Lawson Wong
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 27:480-488
Robots acting in human-scale environments must plan under uncertainty in large state–action spaces and face constantly changing reward functions as requirements and goals change. Planning under uncertainty in large state–action spaces requires hi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03dce84bf8aaef496de537afa5c0ec8a
https://doi.org/10.1609/icaps.v27i1.13867
https://doi.org/10.1609/icaps.v27i1.13867
Publikováno v:
AAAI
We present $\Gamma$-nets, a method for generalizing value function estimation over timescale. By using the timescale as one of the estimator's inputs we can estimate value for arbitrary timescales. As a result, the prediction target for any timescale
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0eee2d3a5111a3c32d016984ed70bf42
http://arxiv.org/abs/1911.07794
http://arxiv.org/abs/1911.07794
Autor:
David Abel, David Hershkowitz, Gabriel Barth-Maron, Stephen Brawner, Kevin O'Farrell, James MacGlashan, Stefanie Tellex
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 25:306-314
Robots that interact with people must flexibly respond to requests by planning in stochastic state spaces that are often too large to solve for optimal behavior. In this work, we develop a framework for goal and state dependent action priors that can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab65b55ed0b916e34e95c1b6276adbe4
https://doi.org/10.1609/icaps.v25i1.13697
https://doi.org/10.1609/icaps.v25i1.13697
Autor:
Bei Peng, Jeff Huang, David L. Roberts, Robert Loftin, Michael L. Littman, Matthew D. Taylor, James MacGlashan
Publikováno v:
Autonomous Agents and Multi-Agent Systems. 30:30-59
For real-world applications, virtual agents must be able to learn new behaviors from non-technical users. Positive and negative feedback are an intuitive way to train new behaviors, and existing work has presented algorithms for learning from such fe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8ef4abe227a9e2a5441ef24e5829a33
https://doi.org/10.1007/s10458-015-9283-7
https://doi.org/10.1007/s10458-015-9283-7
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America. 114(39)
Natural selection designs some social behaviors to depend on flexible learning processes, whereas others are relatively rigid or reflexive. What determines the balance between these two approaches? We offer a detailed case study in the context of a t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6e4cf6d4df7ffa123d8d96ab5b2688e
https://pubmed.ncbi.nlm.nih.gov/28893996
https://pubmed.ncbi.nlm.nih.gov/28893996