Multi-player non-zero-sum games: Online adaptive learning solution of coupled Hamilton-Jacobi equations

By Kyriakos G. Vamvoudakis, Frank L. Lewis. at - Automatisierungstechnik, 2011

489 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/0202f72ae75388e4843f6363348315cfc7bc31e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Electrical and Electronic Engineering

Citations in the corpus

Multi-agent differential graphical games (2011, methodology): “Define the control policy in the formof an actionneural network which computes the control input (41) in the structured form Vamvoudakis and Lewis (2011)”
Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning Method (2017, methodology): “It is known that the optimal consensus control relies on the solution of the coupled Hamilton–Jacobi–Bellman (HJB) equation, which is generally impossible to be solved analytically [8].”
Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers (2012, methodology): “Reinforcement learning techniques have been applied to design adaptive controllers that converge to the solution of two-player zero-sum games in [58], and of multiplayer nonzero-sum games in [59].”
Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP (2013, methodology): “It should be noted that the aforementioned works [28] and [29] are all built on the actor-critic architecture, where two networks referred to as critic network and action network are employed to approximate the optimal cost function and the optimal control policy for each player, respectively.”
Adaptive Dynamic Programming for Control: A Survey and Recent Advances (2021, methodology): “For example, an offline PI algorithm using the actor–critic structure was proposed in [198].”
Leader-Based Optimal Coordination Control for the Consensus Problem of Multiagent Differential Games via Fuzzy Adaptive Dynamic Programming (2015, methodology): “In the early days, game theory was used widely to solve the problem of multiplayer games, such as [18] and [19].”