Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Henryk Michalewski"'
Publikováno v:
Logical Methods in Computer Science, Vol Volume 15, Issue 2 (2019)
We study the strength of axioms needed to prove various results related to automata on infinite words and B\"uchi's theorem on the decidability of the MSO theory of $(N, {\le})$. We prove that the following are equivalent over the weak second-order a
Externí odkaz:
https://doaj.org/article/3f326ee65a9f46fdbb2354808219de3b
Publikováno v:
Electronic Proceedings in Theoretical Computer Science, Vol 223, Iss Proc. ICE 2016, Pp 1-23 (2016)
Subzero automata is a class of tree automata whose acceptance condition can express probabilistic constraints. Our main result is that the problem of determining if a subzero automaton accepts some regular tree is decidable.
Externí odkaz:
https://doaj.org/article/41e1618aa939453283feac141bf52a08
Publikováno v:
Logical Methods in Computer Science, Vol Volume 14, Issue 2, Iss Automata and logic (2018)
We investigate the extension of Monadic Second Order logic, interpreted over infinite words and trees, with generalized "for almost all" quantifiers interpreted using the notions of Baire category and Lebesgue measure.
Externí odkaz:
https://doaj.org/article/186b41138d5b41fa90076fce1bf18ed5
Publikováno v:
ACL/IJCNLP (2)
Imagine you are in a supermarket. You have two bananas in your basket and want to buy four apples. How many fruits do you have in total? This seemingly straightforward question can be challenging for data-driven language models, even if trained at sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b3c0d76fa7a3fa3d25302bfffde05cb
https://doi.org/10.18653/v1/2021.acl-short.49
https://doi.org/10.18653/v1/2021.acl-short.49
Autor:
Adam Jakubowski, Blazej Osinski, Henryk Michalewski, Christopher Galias, Piotr Milos, Silviu Homoceanu, Pawel Ziecina
Publikováno v:
ICRA
We use reinforcement learning in simulation to obtain a driving system controlling a full-size real-world vehicle. The driving policy takes RGB images from a single camera and their semantic segmentation as input. We use mostly synthetic data, with l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c28904fbc806b7c30105da69c6d0fd13
https://doi.org/10.1109/icra40945.2020.9196730
https://doi.org/10.1109/icra40945.2020.9196730
Autor:
Henryk Michalewski, Michał Skrzypczak
Publikováno v:
International Journal of Foundations of Computer Science. 29:911-933
This work is a study of the class of non-deterministic automata on infinite trees that are unambiguous i.e. have at most one accepting run on every tree. The motivating question asks if the fact that an automaton is unambiguous implies some drop in t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80511945fadc485b0b43056f8495b7bb
https://doi.org/10.1142/s012905411842011x
https://doi.org/10.1142/s012905411842011x
Publikováno v:
Electronic Proceedings in Theoretical Computer Science, Vol 223, Iss Proc. ICE 2016, Pp 1-23 (2016)
Subzero automata is a class of tree automata whose acceptance condition can express probabilistic constraints. Our main result is that the problem of determining if a subzero automaton accepts some regular tree is decidable.
In Proceedings ICE 2
In Proceedings ICE 2
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6367d88e72d6f79af0b5185a9d13d697
https://doaj.org/article/41e1618aa939453283feac141bf52a08
https://doaj.org/article/41e1618aa939453283feac141bf52a08
Autor:
Zhihui Lin, Jennifer L. Hicks, Jun Shi, Jiale Chen, Sergey M. Plis, Piotr Jarosik, Sean F. Carroll, Henryk Michalewski, Malte Schilling, Łukasz Kidziński, Chun Yuan, Anton Pechenko, Zhewei Huang, Sergey Kolesnikov, Marcel Salathé, Shuchang Zhou, Piotr Milos, Adam Stelmaszczyk, Andrew Melnik, Zhibo Chen, Blazej Osinski, Sharada P. Mohanty, Mikhail Pavlov, Helge Ritter, Zhizheng Zhang, Zhuobin Zheng, Scott L. Delp, Sergey Levine, Carmichael F. Ong
Publikováno v:
The NIPS '17 Competition: Building Intelligent Systems ISBN: 9783319940410
PUB-Publications at Bielefeld University
PUB-Publications at Bielefeld University
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ade0301b336f2e7f45efb6e5bf81547
https://pub.uni-bielefeld.de/record/2940661
https://pub.uni-bielefeld.de/record/2940661
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319920399
We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage Actor-Critic (BA3C). We show that using the Adam optimizatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcc4c8314835da03cfbdc6d7898f1d86
https://doi.org/10.1007/978-3-319-92040-5_19
https://doi.org/10.1007/978-3-319-92040-5_19
Publikováno v:
Communications in Computer and Information Science ISBN: 9783319759302
CGW@IJCAI
CGW@IJCAI
The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep reinforcement learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca3433eff2bdcb9c9f63b60d247bb7b5
https://doi.org/10.1007/978-3-319-75931-9_1
https://doi.org/10.1007/978-3-319-75931-9_1