Results 91 to 100 of about 5,134 (164)

Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control

open access: yes, 2018
Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks.
Deisenroth, Marc Peter, Kamthe, Sanket
core  

Non-constant discounting in finite horizon: The free terminal time case [PDF]

open access: yes
This paper derives the HJB (Hamilton-Jacobi-Bellman) equation for sophisticated agents in a finite horizon dynamic optimization problem with non-constant discounting in a continuous setting, by using a dynamic programming approach.
Jesus Marin Solano, Jorge Navas Rodenes
core   +1 more source

An optimal-control based integrated model of supply chain [PDF]

open access: yes
Problems of supply chain scheduling are challenged by high complexity, combination of continuous and discrete processes, integrated production and transportation operations as well as dynamics and resulting requirements for adaptability and stability ...
Ivanov, Dmitry
core   +1 more source

Optimal control of a Bose-Einstein condensate in an opticallattice: the non-linear and two-dimensional cases

open access: yesFrontiers in Quantum Science and Technology
We numerically study the optimal control of an atomic Bose-Einstein condensate in an optical lattice. We present two generalizations of the gradient-based algorithm, GRAPE, in the non-linear case and for a two-dimensional lattice.
E. Dionis   +4 more
doaj   +1 more source

Is Thymic Involution Truly a Deterioration or an Adaptation? [PDF]

open access: yesBull Math Biol
Iwasa Y, Hayashi R, Hara A, Matsuo K.
europepmc   +1 more source

Home - About - Disclaimer - Privacy