Zobrazeno 1 - 10
of 2 746
pro vyhledávání: '"P Delage"'
We consider fair resource allocation in sequential decision-making environments modeled as weakly coupled Markov decision processes, where resource constraints couple the action spaces of $N$ sub-Markov decision processes (sub-MDPs) that would otherw
Externí odkaz:
http://arxiv.org/abs/2411.09804
In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in MDPs with st
Externí odkaz:
http://arxiv.org/abs/2410.24128
In restless multi-arm bandits, a central agent is tasked with optimally distributing limited resources across several bandits (arms), with each arm being a Markov decision process. In this work, we generalize the traditional restless multi-arm bandit
Externí odkaz:
http://arxiv.org/abs/2410.23029
The entropic risk measure is widely used in high-stakes decision making to account for tail risks associated with an uncertain loss. With limited data, the empirical entropic risk estimator, i.e. replacing the expectation in the entropic risk measure
Externí odkaz:
http://arxiv.org/abs/2409.19926
This paper develops the geometry of locally bounded rational functions on non-singular real algebraic varieties. First various basic geometric and algebraic results regarding these functions are established in any dimension, culminating with a versio
Externí odkaz:
http://arxiv.org/abs/2409.04232
Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper
Externí odkaz:
http://arxiv.org/abs/2408.13139
X-Ray microtomography of mercury intruded compacted clay: An insight into the geometry of macropores
Autor:
Yuan, Shengyang, Liu, Xianfeng, Wang, Yongxin, Delage, Pierre, Aimedieu, Patrick, Buzzi, Olivier
Publikováno v:
Applied Clay Science, 2022, 227, pp.106573
Soil properties, such as wetting collapse behavior and permeability, are strongly correlated to the soil microstructure. To date, several techniques including mercury intrusion porosimetry (MIP), can be used to characterize the microstructure of soil
Externí odkaz:
http://arxiv.org/abs/2407.21083
Autor:
Chenreddy, Abhilash, Delage, Erick
The field of Contextual Optimization (CO) integrates machine learning and optimization to solve decision making problems under uncertainty. Recently, a risk sensitive variant of CO, known as Conditional Robust Optimization (CRO), combines uncertainty
Externí odkaz:
http://arxiv.org/abs/2403.04670
A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the application of \citeauthor{bellman}'s principle of optimality to solve the sin
Externí odkaz:
http://arxiv.org/abs/2402.02954
Inverse optimization has been increasingly used to estimate unknown parameters in an optimization model based on decision data. We show that such a point estimation is insufficient in a prescriptive setting where the estimated parameters are used to
Externí odkaz:
http://arxiv.org/abs/2402.01489