A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf
.
Filters
Cost Inference for Feedback Dynamic Games from Noisy Partial State Observations and Incomplete Trajectories
[article]
2023
arXiv
pre-print
Prior work on using partial observations to infer the costs in dynamic games assumes an open-loop information pattern. ...
Therefore, we consider the dynamic game cost inference problem under the feedback information pattern, using only partial state observations and incomplete trajectory data. ...
strategies in linear quadratic dynamic games [2] . ...
arXiv:2301.01398v1
fatcat:xchrr5wqgve4vmoh3co3yju7x4
Inferring Objectives in Continuous Dynamic Games from Noise-Corrupted Partial State Observations
[article]
2021
arXiv
pre-print
Our method does not require full observations of game states or player strategies to identify player objectives. Instead, it robustly recovers this information from noisy, partial state observations. ...
Our inverse game solver jointly optimizes player objectives and continuous-state estimates by coupling them through Nash equilibrium constraints. ...
[17] study a special case of an inverse linear-quadratic game in which the equilibrium feedback strategies of all but one player are known. ...
arXiv:2106.03611v3
fatcat:sbyznmeze5bybjmloyip5r3fli
Table of Contents
2020
IEEE Transactions on Automatic Control
Su 5344 State Observers for Systems Subject to Bounded Disturbances Using Quadratic Boundedness . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ...
Boem 5352 Adaptive State-Feedback Stabilization of Stochastic High-Order Nonlinear Systems With Time-Varying Powers and Stochastic Inverse Dynamics . . . . . . . . . . . . . . . . . . . . . . . . . . . ...
doi:10.1109/tac.2020.3032246
fatcat:53ud3j7ysfg7pboxxpepokwn2q
Learning Players' Objectives in Continuous Dynamic Games from Partial State Observations
[article]
2023
arXiv
pre-print
In this work, we address this issue by proposing a novel method for learning players' objectives in continuous dynamic games from noise-corrupted, partial state observations. ...
Dynamic game theory provides a powerful mathematical framework for modeling scenarios in which agents have individual objectives and interactions evolve over time. ...
Running example: Consider an N = 2-player linearquadratic (LQ) game-i.e., one in which dynamics f t are linear in state x t and control inputs u t , and costs J i are quadratic in states and controls. ...
arXiv:2302.01999v1
fatcat:4ieoemp6bve3rjgodtlmiuwn7u
Predictive Inverse Optimal Control for Linear-Quadratic-Gaussian Systems
2015
International Conference on Artificial Intelligence and Statistics
Its usefulness has been established in a number of large-scale sequential decision settings characterized by complete state observability. ...
Though extensions of predictive inverse optimal control to partially observable Markov decision processes have been developed, their applicability has been limited by the complexities of inference in those ...
Background & Related Work
Linear quadratic Gaussian control Linear-quadratic-Gaussian (LQG) control problems seek the optimal control policy of partially observed linear systems. ...
dblp:conf/aistats/ChenZ15
fatcat:xkshkxw5bbck5enwx27euabf24
Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions
[article]
2021
arXiv
pre-print
In this paper, we study the problem of multiple stochastic agents interacting in a dynamic game scenario with continuous state and action spaces. ...
In both cases, we show that, by taking into account the agents' game theoretic interactions using our algorithm, a more accurate model of agents' costs can be learned, compared with standard inverse optimal ...
|s t ), since the dynamics are linear and the cost is quadratic, the expectation of the terms define the class of linear quadratic games where the dynamics are linear and the stage costs are quadratic ...
arXiv:2110.01027v1
fatcat:4gcjwievrbcf3erlm4lmydklca
Chance-Constrained Iterative Linear-Quadratic Stochastic Games
[article]
2022
arXiv
pre-print
In this paper, we propose the chance-constrained iterative linear-quadratic stochastic games (CCILQGames) algorithm. ...
Dynamic game arises as a powerful paradigm for multi-robot planning, for which safety constraint satisfaction is crucial. ...
Our work builds upon the iterative linear-quadratic game method and extends to stochastic games with dynamics and observation uncertainty. ...
arXiv:2203.01222v3
fatcat:7xkkoxoczvebfifse6ewrh6q6a
Page 384 of Mathematical Reviews Vol. , Issue 85a
[page]
1985
Mathematical Reviews
Bagchi, Arunabha (1-UCLA-F); Olsder, Geert Jan (NL-TWEN-A) Numerical approaches to linear-quadratic differential games with imperfect observations. ...
Using our method, a stochastic system with n
states is decomposed into m (m > n—1) component systems where
each system has two states. ...
An Iterative Quadratic Method for General-Sum Differential Games with Feedback Linearizable Dynamics
[article]
2020
arXiv
pre-print
Iterative linear-quadratic (ILQ) methods are widely used in the nonlinear optimal control community. ...
Recent work has applied similar methodology in the setting of multiplayer general-sum differential games. ...
We observe that solving the game using feedback linearization converges much more reliably than solving it for the original nonlinear system. ...
arXiv:1910.00681v2
fatcat:nftwhyrr5vf7tphjswejis5t2a
Inverse linear-quadratic nonzero-sum differential games
[article]
2024
arXiv
pre-print
This paper addresses the inverse problem for Linear-Quadratic (LQ) nonzero-sum N-player differential games, where the goal is to learn parameters of an unknown cost function for the game, called observed ...
Towards this end, using the demonstrated data, a synthesized game needs to be constructed, which is required to be equivalent to the observed game in the sense that the trajectories generated by the equilibrium ...
There are various works dedicated to the inverse problem for non-cooperative linear-quadratic differential games. ...
arXiv:2310.05631v3
fatcat:wl6c45lmazetbiw4hl4zaewhtm
Mutually Quadratically Invariant Information Structures in Two-Team Stochastic Dynamic Games
[article]
2016
arXiv
pre-print
We formulate a two-team linear quadratic stochas- tic dynamic game featuring two opposing teams each with decentralized information structures. ...
We show that, for zero-sum two- team dynamic games, structured state feedback Nash (saddle- point) equilibrium strategies can be computed from equivalent structured disturbance feedforward saddle point ...
CONCLUSION We have considered a two-team linear quadratic stochastic dynamic game with decentralized information structures for both teams. ...
arXiv:1607.05426v1
fatcat:eheojxsm55fofio2lfta3yrx7a
2015 Index IEEE Transactions on Automatic Control Vol. 60
2015
IEEE Transactions on Automatic Control
., +, TAC Dec. 2015 3373-3378
Linear quadratic control
A Linear-Quadratic Optimal Control Problem of Forward-Backward Sto-
chastic Differential Equations With Partial Information. ...
., +, TAC May 2015 1422-1426 Open-Loop Nash Equilibria in a Class of Linear-Quadratic Difference Games With Constraints. ...
doi:10.1109/tac.2015.2512305
fatcat:5gut6qeomfh73fwfvehzujbr5q
Inverse noncooperative differential games
2017
2017 IEEE 56th Annual Conference on Decision and Control (CDC)
We may therefore apply the standard tools of linear quadratic (LQ) optimal control to solve our inverse differential game problem (regardless of the linearity of the system dynamics (1)). ...
Assumptions 1 and 2 are conditions on the dynamics and cost functional of the game that are trivially satisfied by linear dynamics with quadratic cost functional. ...
doi:10.1109/cdc.2017.8264504
dblp:conf/cdc/MolloyFP17
fatcat:q77nmno36vebhg4ozxbzgz3r6m
The Inverse Problem of Linear-Quadratic Differential Games: When is a Control Strategies Profile Nash?
[article]
2022
arXiv
pre-print
This paper aims to formulate and study the inverse problem of non-cooperative linear quadratic games: Given a profile of control strategies, find cost parameters for which this profile of control strategies ...
Using the Kalman equation, we also show the leader can enforce the same Nash profile by applying penalties on the shared state instead of penalizing the player for other players' actions to avoid the impression ...
In this paper, we study the inverse problem of noncooperative linear-quadratic differential games. ...
arXiv:2207.05303v2
fatcat:ovw2siv5l5eavfslcr7miiytfa
On Aronsson Equation and Deterministic Optimal Control
2008
Applied Mathematics and Optimization
The methodology uses a Piecewise Linear (PWL) approximation of the Ordinary Differential Equations (ODEs) vector field which describes the dynamics of a system parameterized by the control inputs in order ...
CP2 Differential Game Between Manufacturer, Retailer, and Bank We consider a differential game between manufacturer, retailer, and bank. ...
In this paper, we use a zero-sum game theoretical approach to address the robust disturbance attenuation analysis of state feedback Nash strategies for Dynamic Linear Quadratic Sequential Games (LQSGs) ...
doi:10.1007/s00245-008-9048-7
fatcat:kihxqtczfzdn5pbmvsd42axbk4
« Previous
Showing results 1 — 15 out of 10,250 results