Zobrazeno 1 - 10
of 1 263
pro vyhledávání: '"Stas, P."'
The reward function is an essential component in robot learning. Reward directly affects the sample and computational complexity of learning, and the quality of a solution. The design of informative rewards requires domain knowledge, which is not alw
Externí odkaz:
http://arxiv.org/abs/2411.13613
Autor:
Yada, Toshihiro, Stas, Pieter-Jan, Suleymanzade, Aziza, Knall, Erik N., Yoshioka, Nobuyuki, Sagawa, Takahiro, Lukin, Mikhail D.
Thermodynamic principles governing energy and information are important tools for a deeper understanding and better control of quantum systems. In this work, we experimentally investigate the interplay of the thermodynamic costs and information flow
Externí odkaz:
http://arxiv.org/abs/2411.06709
Return words are a classical tool for studying shift spaces with low factor complexity. In recent years, their projection inside groups have attracted some attention, for instance in the context of dendric shift spaces, of generation of pseudorandom
Externí odkaz:
http://arxiv.org/abs/2410.12534
Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric, allowing fo
Externí odkaz:
http://arxiv.org/abs/2408.07507
Global Navigation Satellite Systems (GNSS) aided Inertial Navigation System (INS) is a fundamental approach for attaining continuously available absolute vehicle position and full state estimates at high bandwidth. For transportation applications, st
Externí odkaz:
http://arxiv.org/abs/2407.13912
Autor:
Lian, Xinyu, Jacobs, Sam Ade, Kurilenko, Lev, Tanaka, Masahiro, Bekman, Stas, Ruwase, Olatunji, Zhang, Minjia
Existing checkpointing approaches seem ill-suited for distributed training even though hardware limitations make model parallelism, i.e., sharding model state across multiple accelerators, a requirement for model scaling. Consolidating distributed mo
Externí odkaz:
http://arxiv.org/abs/2406.18820
An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any
Externí odkaz:
http://arxiv.org/abs/2406.18033
Dendric shift spaces simultaneously generalize codings of regular interval exchanges and episturmian shift spaces, themselves both generalizations of Sturmian words. One of the key properties enforced by dendricity is the Return Theorem. In this pape
Externí odkaz:
http://arxiv.org/abs/2406.15075
Computational descriptions of purposeful behavior comprise both descriptive and normative} aspects. The former are used to ascertain current (or future) states of the world and the latter to evaluate the desirability, or lack thereof, of these states
Externí odkaz:
http://arxiv.org/abs/2406.14476
Publikováno v:
Publ. Astron. Soc. Aust. 41 (2024) e022
We investigate the connection between a cluster's structural configuration and observable measures of its gas emission that can be obtained in X-ray and Sunyaev-Zeldovich (SZ) surveys. We present an analytic model for the intracluster gas density pro
Externí odkaz:
http://arxiv.org/abs/2403.09946