Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Philip S. Thomas"'
Autor:
Philip S. Thomas
How is life possible in a world of evil, suffering, and chaos? Christians have historically been inept at offering adequate answers as to why people's lives are derailed by sudden chaos and, even worse, at equipping people to live in the throes, or a
Publikováno v:
RecSys
We propose AC-CRS, a novel conversational recommendation system based on reinforcement learning that better models user interaction compared to prior work. Interactive recommender systems expect an initial request from a user and then iterate by aski
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed171237b9a48a65ed1cd709301c2d09
https://doi.org/10.1145/3460231.3474271
https://doi.org/10.1145/3460231.3474271
Autor:
Philip S. Thomas, Emma Brunskill, Bruno da Silva, Andrew G. Barto, Stephen Giguere, Yuriy Brun
Publikováno v:
Science. 366:999-1004
Making well-behaved algorithmsMachine learning algorithms are being used in an ever-increasing number of applications, and many of these applications affect quality of life. Yet such algorithms often exhibit undesirable behavior, from various types o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7eed9b40674628fdd383b28489b12ee
https://doi.org/10.1126/science.aag3311
https://doi.org/10.1126/science.aag3311
Autor:
Philip S. Thomas
There is a complex relationship between the meaning of Scripture and the ways it is used. Sometimes the meaning constrains Scripture's use, and sometimes Scripture's use casts new and fresh light onto its meaning. Theologians and biblical scholars o
Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before deployment, to e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5de6b4d6f92be84fcf260b68ba0c9b3a
Publikováno v:
AAAI
In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fcb8a8092a698594b5d2b5826050e8ee
Autor:
Michael S. Branicky, Philip S. Thomas, Kathleen M. Jagodnik, Antonie J. van den Bogert, Robert F. Kirsch
Publikováno v:
IEEE Transactions on Human-Machine Systems. 46:723-733
High-level spinal cord injury (SCI) in humans causes paralysis below the neck. Functional electrical stimulation (FES) technology applies electrical current to nerves and muscles to restore movement, and controllers for upper extremity FES neuroprost
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::faf64a57b4a7c22e0538f7a6404773e7
https://doi.org/10.1109/thms.2016.2558630
https://doi.org/10.1109/thms.2016.2558630
Publikováno v:
IJCAI
We consider the problem of off-policy policy selection in reinforcement learning: using historical data generated from running one policy to compare two or more policies. We show that approaches based on importance sampling can be unfair---they can s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::214e8c96b4283043d679453bb3b90221
https://doi.org/10.24963/ijcai.2018/729
https://doi.org/10.24963/ijcai.2018/729
Autor:
Philip S. Thomas, Michael S. Branicky, Kathleen M. Jagodnik, Robert F. Kirsch, Antonie J. van den Bogert
Publikováno v:
IEEE Trans Neural Syst Rehabil Eng
Functional Electrical Stimulation (FES) employs neuroprostheses to apply electrical current to the nerves and muscles of individuals paralyzed by spinal cord injury (SCI) to restore voluntary movement. Neuroprosthesis controllers calculate stimulatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6dd1085056172c28b2c471d34dbac95
https://pubmed.ncbi.nlm.nih.gov/28475063
https://pubmed.ncbi.nlm.nih.gov/28475063
Publikováno v:
WWW (Companion Volume)
The main objective in the ad recommendation problem is to find a strategy that, for each visitor of the website, selects the ad that has the highest probability of being clicked. This strategy could be computed using supervised learning or contextual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f4a9fa7962db7181ca533f90a807c09
https://doi.org/10.1145/2740908.2741998
https://doi.org/10.1145/2740908.2741998