mlsanityData to 7 Oct 2026

An active learning method for solving competitive multi-agent decision-making and control problems

arXiv 2212.12561 ↗First posted 23 Dec 2022eess.SY cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions and recursively update simple local parametric estimates of the action-reaction mappings. Under very general working assumptions (not even assuming that a stationary profile exists), sufficient conditions are established to assess the asymptotic properties of the proposed active learning methodology so that, if the parameters characterizing the action-reaction mappings converge, a stationary action profile is achieved. Such conditions hence act also as certificates for the existence of such a profile. Extensive numerical simulations involving typical competitive multi-agent control and decision-making problems illustrate the practical effectiveness of the proposed learning-based approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 69 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

18 of 69 references.

References · 18

  1. 2019Global optimization via inverse distance weighting and radial basis functionscited by 16
  2. 2021Reliably-stabilizing piecewise-affine neural network controllerscited by 13
  3. 2016A Bayesian optimization approach to find Nash equilibriacited by 9
  4. 2022Active Learning for Regression by Inverse Distance Weightingcited by 9
  5. 2013Learning Equilibria of Games via Payoff Queriescited by 8
  6. 2019Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spacescited by 8
  7. 2021Recurrent Neural Network Training with Convex Loss and Regularization Functions by Extended Kalman Filteringcited by 8
  8. 2013Query Complexity of Approximate Nash Equilibriacited by 6
  9. 2013On the Communication Complexity of Approximate Nash Equilibriacited by 5
  10. 2013The Query Complexity of Correlated Equilibriacited by 5
  11. 2019Charging plug-in electric vehicles as a mixed-integer aggregative gamecited by 4
  12. 2016Dynamic control of agents playing aggregative games with coupling constraintscited by 3
6 more
  1. 2018Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approachcited by 3
  2. 2021Efficient Learning of a Linear Dynamical System with Stability Guaranteescited by 3
  3. 2018Learning Convex Partitions and Computing Game-theoretic Equilibria from Best Response Queriescited by 2
  4. 2021Learning equilibria with personalized incentives in a class of nonmonotone gamescited by 2
  5. 2022Distributed Stochastic Nash Equilibrium Learning in Locally Coupled Network Games with Unknown Parameterscited by 2
  6. 2022Personalized incentives as feedback design in generalized Nash equilibrium problemscited by 1

Built on by

Not cited yet.