Multi-agent natural actor-critic reinforcement learning algorithms
Year of publication: |
2023
|
---|---|
Authors: | Trivedi, Prashant ; Hemachandra, Nandyala |
Published in: |
Dynamic games and applications : DGA. - Boston : Birkhäuser, ISSN 2153-0793, ZDB-ID 2581474-6. - Vol. 13.2023, 1, p. 25-55
|
Subject: | Actor-Critic Methods | Algorithms for better local minima | Fisher Information Matrix | Function Approximations | Local optima value comparison | Natural Gradients | Networked Agents | Non-Convex Optimization | Quasi second-order methods | Stochastic Approximations | Traffic Network Control | Algorithmus | Algorithm | Agentenbasierte Modellierung | Agent-based modeling | Mathematische Optimierung | Mathematical programming | Schätztheorie | Estimation theory | Stochastischer Prozess | Stochastic process |
-
Comparison of Kriging-based algorithms for simulation optimization with heterogeneous noise
Jalali, Hamed, (2017)
-
D-optimal Data Fusion : exact and approximation algorithms
Li, Yongchun, (2024)
-
Exact numerical algorithms for linear stochastic wave equation and stochastic Klein-Gordon equation
Martin, A., (2003)
- More ...
-
Quest for measurement : the achilles heel of policies for "inclusive growth"
Trivedi, Prashant, (2012)
-
A conceptual model for driving green purchase among Indian consumers
Trivedi, Prashant, (2015)
-
Iyer, Krishnamurthy, (2010)
- More ...