Learning in mean-field games

H Yin, PG Mehta, SP Meyn… - IEEE Transactions on …, 2013‏ - ieeexplore.ieee.org
The purpose of this paper is to show how insight obtained from a mean-field model can be
used to create an architecture for approximate dynamic programming (ADP) for a certain …

Joint admission control and routing via approximate dynamic programming for streaming video over software-defined networking

J Yang, K Zhu, Y Ran, W Cai… - IEEE Transactions on …, 2016‏ - ieeexplore.ieee.org
This paper considers the optimization problem of joint admission control and routing for the
video streaming service in wired software-defined networking (SDN). With the aid of the …

Differential temporal difference learning

AM Devraj, I Kontoyiannis… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
Value functions derived from Markov decision processes arise as a central component of
algorithms as well as performance metrics in many statistics and engineering applications of …

Learning techniques for feedback particle filter design

A Radhakrishnan, A Devraj… - 2016 IEEE 55th …, 2016‏ - ieeexplore.ieee.org
The feedback particle filter (FPF) is an approach to estimating the posterior distribution of the
states in a process-observation model. As in other versions of the particle filter, Monte Carlo …

Differential TD learning for value function approximation

AM Devraj, SP Meyn - 2016 IEEE 55th Conference on Decision …, 2016‏ - ieeexplore.ieee.org
Value functions arise as a component of algorithms as well as performance metrics in
statistics and engineering applications. Computation of the associated Bellman equations is …

Quasi-stochastic approximation and off-policy reinforcement learning

A Bernstein, Y Chen, M Colombino… - 2019 IEEE 58th …, 2019‏ - ieeexplore.ieee.org
The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic
frameworks for reinforcement learning (RL), and often an efficient approach to solving (or …

Coordinating dispatch of distributed energy resources with model predictive control and Q-learning

A Kowli, E Mayhorn, K Kalsi… - … Science Laboratory Report …, 2012‏ - ideals.illinois.edu
Distributed energy resources such as renewable generators (wind, solar), energy storage,
and demand response can be used to complement fossil-fueled generators. The uncertainty …

Optimal rate of convergence for quasi-stochastic approximation

A Bernstein, Y Chen, M Colombino… - arxiv preprint arxiv …, 2019‏ - arxiv.org
The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic
frameworks for reinforcement learning (RL), and often an efficient approach to solving (or …

The ieee computer society smart grid vision project opens opportunites for computational intelligence

D Cartes, JH Chow, D McCaugherty… - … IEEE Conference on …, 2013‏ - ieeexplore.ieee.org
The IEEE Computer Society Smart Grid Vision Project (CS-SGVP) was chartered to develop
Smart Grid visions looking forward as far as 30 years into the future. At the completion of the …

[ספר][B] Reinforcement learning techniques for controlling resources in power networks

AS Kowli - 2013‏ - search.proquest.com
As power grids transition towards increased reliance on renewable generation, energy
storage and demand response resources, an effective control architecture is required to …