Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Matthew C. Fontaine"'
Publikováno v:
ACM Transactions on Human-Robot Interaction. 11:1-30
The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applications. Exploring diverse scenarios of humans and robots interacting i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46760ecb816046ddc3775d0a5b80b083
https://doi.org/10.1145/3476412
https://doi.org/10.1145/3476412
Publikováno v:
IEEE Transactions on Haptics. 15:508-520
Data-driven texture modeling and rendering has pushed the limit of realism in haptics. However, the lack of haptic texture databases, difficulties of model interpolation and expansion, and the complexity of real textures prevent data-driven methods f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dbf82ceb5b156ed2334b2738e8cfce63
https://doi.org/10.1109/toh.2022.3173935
https://doi.org/10.1109/toh.2022.3173935
Autor:
Matthew C. Fontaine, Ruilin Liu, Ahmed Khalifa, Jignesh Modi, Julian Togelius, Amy K. Hoover, Stefanos Nikolaidis
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:5922-5930
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar to human-authored examples, human designers often want to explore the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::faab8ed680cac45539428297f75a62df
https://doi.org/10.1609/aaai.v35i7.16740
https://doi.org/10.1609/aaai.v35i7.16740
We study the problem of efficiently generating high-quality and diverse content in games. Previous work on automated deckbuilding in Hearthstone shows that the quality diversity algorithm MAP-Elites can generate a collection of high-performing decks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7bd0c06296008d8467d93e110d6aaed4
http://arxiv.org/abs/2112.03534
http://arxiv.org/abs/2112.03534
Autor:
Matthew C. Fontaine
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:12876-12877
My work studies the problem of generating scenarios to evaluate interaction between humans and robots. I expect these interactions to grow in complexity as robots become more intelligent and enter our daily lives. However, evaluating such interaction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::891a82f3d963f777968d3567497ef900
https://doi.org/10.1609/aaai.v36i11.21575
https://doi.org/10.1609/aaai.v36i11.21575
Publikováno v:
Robotics: Science and Systems
The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applications. Exploring diverse scenarios of humans and robots interacting i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e8c1522fe8b06525dda279b25ff62220
https://doi.org/10.15607/rss.2021.xvii.036
https://doi.org/10.15607/rss.2021.xvii.036
Publikováno v:
Robotics: Science and Systems
When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks. However, less emphasis has been placed on the effect of the environment on coordination
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::49ee2684a1395c95e73ffabe9dabdf86
http://arxiv.org/abs/2106.10853
http://arxiv.org/abs/2106.10853
Publikováno v:
GECCO
We focus on the challenge of finding a diverse collection of quality solutions on complex continuous domains. While quality diver-sity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are designed to generate a diverse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcc6e571342b11ba53f2942046c27cc0
http://arxiv.org/abs/1912.02400
http://arxiv.org/abs/1912.02400
Autor:
Matthew C. Fontaine
Publikováno v:
Olympiads in Informatics. 12:25-41
Among the most interesting problems in competitive programming involve maximum flows. However, efficient algorithms for solving these problems are often difficult for students to understand at an intuitive level. One reason for this difficulty may be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b9b3a8d3af8880421c2d33d87bdbdb9
https://doi.org/10.15388/ioi.2018.03
https://doi.org/10.15388/ioi.2018.03
Autor:
Julian Togelius, L. B. Soros, Amy K. Hoover, Scott Lee, Fernando de Mesentier Silva, Matthew C. Fontaine
Publikováno v:
GECCO
Quality diversity (QD) algorithms such as MAP-Elites have emerged as a powerful alternative to traditional single-objective optimization methods. They were initially applied to evolutionary robotics problems such as locomotion and maze navigation, bu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a4ac6c8624d8832297363baf85b8543
https://doi.org/10.1145/3321707.3321794
https://doi.org/10.1145/3321707.3321794