Zobrazeno 1 - 10
of 788
pro vyhledávání: '"Sapora, A"'
We present an empirical study investigating how specific properties of preference datasets, such as mixed-quality or noisy data, affect the performance of Preference Optimization (PO) algorithms. Our experiments, conducted in MuJoCo environments, rev
Externí odkaz:
http://arxiv.org/abs/2411.06568
Often times in imitation learning (IL), the environment we collect expert demonstrations in and the environment we want to deploy our learned policy in aren't exactly the same (e.g. demonstrations collected in simulation but deployment in the real wo
Externí odkaz:
http://arxiv.org/abs/2406.11905
Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived through the selection of a mirror map and enjoy finite-time convergence
Externí odkaz:
http://arxiv.org/abs/2402.05187
Autor:
Frey, Sascha, Li, Kang, Nagy, Peer, Sapora, Silvia, Lu, Chris, Zohren, Stefan, Foerster, Jakob, Calinescu, Anisoara
Financial exchanges across the world use limit order books (LOBs) to process orders and match trades. For research purposes it is important to have large scale efficient simulators of LOB dynamics. LOB simulators have previously been implemented in t
Externí odkaz:
http://arxiv.org/abs/2308.13289
Autor:
Nagy, Peer, Frey, Sascha, Sapora, Silvia, Li, Kang, Calinescu, Anisoara, Zohren, Stefan, Foerster, Jakob
Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that genera
Externí odkaz:
http://arxiv.org/abs/2309.00638
Publikováno v:
In Composites Science and Technology 8 February 2024 246
Autor:
Ahlgren, John, Berezin, Maria Eugenia, Bojarczuk, Kinga, Dulskyte, Elena, Dvortsova, Inna, George, Johann, Gucevska, Natalija, Harman, Mark, He, Shan, Lämmel, Ralf, Meijer, Erik, Sapora, Silvia, Spahr-Summers, Justin
Software-intensive organizations rely on large numbers of software assets of different types, e.g., source-code files, tables in the data warehouse, and software configurations. Who is the most suitable owner of a given asset changes over time, e.g.,
Externí odkaz:
http://arxiv.org/abs/2004.07352
Autor:
Ahlgren, John, Berezin, Maria Eugenia, Bojarczuk, Kinga, Dulskyte, Elena, Dvortsova, Inna, George, Johann, Gucevska, Natalija, Harman, Mark, Lämmel, Ralf, Meijer, Erik, Sapora, Silvia, Spahr-Summers, Justin
We introduce the Web-Enabled Simulation (WES) research agenda, and describe FACEBOOK's WW system. We describe the application of WW to reliability, integrity and privacy at FACEBOOK , where it is used to simulate social media interactions on an infra
Externí odkaz:
http://arxiv.org/abs/2004.05363
Publikováno v:
In European Journal of Mechanics / A Solids September-October 2023 101
Publikováno v:
In International Journal of Fatigue August 2023 173