Results 141 to 149 of about 1,967 (149)

Erratum: Asynchronous Stochastic Approximations

SIAM Journal on Control and Optimization, 2000
The proofs of Lemma 2.1 and Theorem 3.2 of [1] have a common error, the correction of which needs additional conditions: the use of l’Hopital’s rule in both equates the limiting ratio of derivatives of functions with the limiting ratio of the functions themselves, but this presupposes that the latter exist.
openaire   +1 more source

Asynchronous Gossip Algorithm for Stochastic Optimization with Approximate Projections: Constant Stepsize Analysis

2018 37th Chinese Control Conference (CCC), 2018
This paper considers the problem of minimizing the sum of convex functions over a network when each component function is known (with stochastic errors) to a specific network agent. We need to note that the objective function is strongly convex in this paper. To speed up computations we use adaptive approximate projections only requiring to move within
Ye Yuan, Xiangpeng Xie
openaire   +1 more source

Stochastic Reactive Production Scheduling by Multi-agent Based Asynchronous Approximate Dynamic Programming

2005
The paper investigates a stochastic production scheduling problem with unrelated parallel machines. A closed-loop scheduling technique is presented that on-line controls the production process. To achieve this, the scheduling problem is reformulated as a special Markov Decision Process. A near-optimal control policy of the resulted MDP is calculated in
Balázs Csanád Csáji, László Monostori   +1 more
openaire   +1 more source

Concentration of Contractive Stochastic Approximation and Reinforcement Learning

Stochastic Systems, 2022
Siddharth Chandak, Vivek S Borkar, Parth Dodhia   +2 more
exaly  

Asynchronous l2–l∞ filtering for discrete-time stochastic Markov jump systems with randomly occurred sensor nonlinearities

Automatica, 2014
Zheng-Guang Wu, Peng Shi, Hongye Su
exaly  

Asynchronous Stochastic Approximation and Average-Reward Reinforcement Learning.

CoRR
Huizhen Yu, Yi Wan 0004, Richard S. Sutton   +2 more
openaire   +1 more source

On Input-to-State Stability of Switched Stochastic Nonlinear Systems Under Extended Asynchronous Switching

IEEE Transactions on Cybernetics, 2016
Yu Kang, Di-Hua Zhai, Guo-Ping Liu
exaly  

Asynchronous stochastic approximation and Q-learning

J N Tsitsiklis
exaly  

Distributed asynchronous stochastic approximation algorithms with unbounded stochastic information delays - theory and applications (Verteilte asynchrone stochastische Approximationsalgorithmen mit unbeschränkten stochastischen Informationsdelays - Theorie und Anwendungen)

openaire   +1 more source