Hybrid Mean Field Learning in Large-Scale Dynamic Robust Games

Abstract : One of the objectives in distributed interacting multi-player systems is to enable a collection of different players to achieve a desirable objective. There are two overriding challenges to achieving this objective: The first one is related to the complexity of finding optimal solution. A centralized algorithm may be prohibitively complex when there are large number of interacting players. This motivates the use of adaptive methods that enable players to self-organize into suitable, if not optimal, alternative solutions. The second challenge is limited information. Players may have limited knowledge about the status of other players, except perhaps for a small subset of neighboring players. The limitations in term of information induce robust stochastic optimization, bounded rationality and inconsistent beliefs. In this work, we investigate asymptotic pseudo-trajectories of large-scale dynamic robust games under various COmbined fully DIstributed PAyoff and Strategy Reinforcement Learning (CODIPAS-RL) under outdated noisy measurement and random updates. Extension to continuous action space is discussed.
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00643517
Contributor : Catherine Magnet <>
Submitted on : Tuesday, November 22, 2011 - 10:36:49 AM
Last modification on : Thursday, March 29, 2018 - 11:06:05 AM
Long-term archiving on : Thursday, February 23, 2012 - 2:21:28 AM

File

coia.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00643517, version 1

Collections

Citation

Hamidou Tembine, Mohamad Assaad. Hybrid Mean Field Learning in Large-Scale Dynamic Robust Games. AMS International Conference on Control and Optimization with Industrial Applications, Aug 2011, Ankara, Turkey. 2 p. ⟨hal-00643517⟩

Share

Metrics

Record views

290

Files downloads

89