Results 91 to 100 of about 2,468,749 (240)
Advanced Intelligent Systems, EarlyView.A hybrid Reinforcement Learning–Explainable AI framework integrates SHAP and LIME explanations directly into a Deep Q‐Network inference loop for real‐time ICU decision support. Trained on 18 142 mechanically ventilated stays from the eICU database, the system attains 93.0% decision accuracy, 20% fewer errors than RL alone, and a 91% clinician trust ...
Jannatul Ferdaus Disha +2 more
wiley +1 more source
N-Player Stochastic Differential Games [PDF]
SIAM Journal on Control and Optimization, 1976 The paper presents conditions which guarantee that the control strategies adopted by N players constitute an efficient solution, an equilibrium, or a core solution. The system dynamics are described by an Ito equation, and all players have perfect information.
openaire +2 more sources
Stopping games: recent results [PDF]
We survey recent results on the existence of the value in zero-sum stopping games with discrete and continuous time, and on the existence of e-equilibria in non zero-sum games with discrete time.stopping games; stochastic games ...
VIEILLE, Nicolas, SOLAN, Eilon
core
Learning in perturbed asymmetric games [PDF]
, 2004 We investigate the stability of mixed strategy equilibria in 2 person (bimatrix) games under perturbed best response dynamics. A mixed equilibrium is asymptotically stable under all such dynamics if and only if the game is linearly equivalent to a zero ...
Hopkins, E +5 more
core
Accounting for animal health in efficiency analysis: An application to Swedish dairy farms
American Journal of Agricultural Economics, EarlyView.Abstract Poor animal health is a central concern in modern livestock production. Despite the necessity to incorporate animal health in efficiency analysis, the theoretical and empirical developments are limited on this subject. This article appropriately characterizes the axiomatic properties of animal health within a production framework.
Frederic Ang +3 more
wiley +1 more source
Risk sensitive stochastic control and differential games [PDF]
Communications in Information and Systems, 2006 We give a concise introduction to risk sensitive control of Markov diffusion processes and related two-controller, zero-sum differential games. The method of dynamic programming for the risk sensitive control problem leads to a nonlinear partial differential equation of Hamilton-Jacobi-Bellman type. In the totally risk sensitive limit, this becomes the
openaire +2 more sources
Convexity, Differential Equations, and Games [PDF]
Theoretical and experimental studies of noncooperative games increasingly recognize Nash equilibrium as a limiting outcome of players‘ repeated interaction. This note, while sharing that view, illustrates and advocates combined use of convex optimization
Sjur Didrik Flåm
core
Polarization‐Dependence of Nonlinear Optical Effects in Silicon: The Case of Ultrafast Processing
Advanced Physics Research, EarlyView.The dependence of the input polarization for the nonlinear optical propagation in silicon is investigated theoretically and experimentally. The perturbative regime is examined using pump‐probe shadowgraphy and nonlinear transmission, whereas the case of permanent laser‐induced modifications is addressed using a combination of Raman micro‐spectroscopy ...
Namig Alasgarzade +6 more
wiley +1 more source
A theory of regular Markov perfect equilibria in dynamic stochastic games: genericity, stability, and purification [PDF]
This paper studies generic properties of Markov perfect equilibria in dynamic stochastic games. We show that almost all dynamic stochastic games have a finite number of locally isolated Markov perfect equilibria.
Doraszelski, Ulrich, Escobar, Juan
core
New approach to stochastic optimal control and applications to economics [PDF]
, 2005 This paper provides new insights into the solution of optimal stochastic control problems by means of a system of partial differential equations, which characterize directly the optimal control.
Rincón-Zapatero, Juan Pablo +1 more
core +1 more source