Zobrazeno 1 - 10
of 96
pro vyhledávání: '"da Silva, Bruno C."'
Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each optimized for a
Externí odkaz:
http://arxiv.org/abs/2301.07784
Autor:
da Silva, Bruno C, Momtaz, Zahra S, Bruas, Lucas, Rouviére, Jean-Luc, Okuno, Hanako, Cooper, David, Den-Hertog, Martien I
Publikováno v:
Applied Physics Letters, American Institute of Physics, 2022, 121 (12), pp.123503
Momentum resolved 4D-STEM, also called center of mass (CoM) analysis, has been used to measure the long range built-in electric field of a silicon p-n junction. The effect of different STEM modes and the trade-off between spatial resolution and elect
Externí odkaz:
http://arxiv.org/abs/2211.00971
Autor:
da Silva, Bruno C., Momtaz, Zahra S., Monroy, Eva, Okuno, Hanako, Rouviere, Jean-Luc, Cooper, David, den-Hertog, Martien I.
A key issue in the development of high-performance semiconductor devices is the ability to properly measure active dopants at the nanometer scale. 4D scanning transmission electron microscopy and off-axis electron holography have opened up the possib
Externí odkaz:
http://arxiv.org/abs/2209.09633
In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set of polici
Externí odkaz:
http://arxiv.org/abs/2206.11326
Publikováno v:
Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems. 2021. 97-105
Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes performance o
Externí odkaz:
http://arxiv.org/abs/2105.09452
Publikováno v:
PeerJ Computer Science 2021
In reinforcement learning (RL), dealing with non-stationarity is a challenging issue. However, some domains such as traffic optimization are inherently non-stationary. Causes for and effects of this are manifold. In particular, when dealing with traf
Externí odkaz:
http://arxiv.org/abs/2004.04778
In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but relate
Externí odkaz:
http://arxiv.org/abs/1711.09048
Publikováno v:
In Information and Software Technology August 2021 136
Publikováno v:
In Computers in Biology and Medicine February 2021 129
Autor:
Calegari, Francyelle, da Silva, Bruno C., Tedim, João, Ferreira, Mário G.S., Berton, Marcos A.C., Marino, Cláudia E.B.
Publikováno v:
In Progress in Organic Coatings January 2020 138