|
| | | | |
| | | |
| Stat |
Members: 3669
Articles: 2'599'751
Articles rated: 2609
18 March 2025 |
|
| | | | |
|
Article overview
| |
|
|
Fictitious Play with Inertia Learns Pure Equilibria in Distributed Games with Incomplete Information | | Brian Swenson
; Ceyhun Eksin
; Soummya Kar
; Alejandro Ribeiro
; | | Date: |
2 May 2016 | | Abstract: | The paper studies algorithms for learning pure-strategy Nash equilibria (NE)
in networked multi-agent systems with uncertainty. In many such real-world
systems, information is naturally distributed among agents and must be
disseminated using a sparse inter-agent communication infrastructure. The paper
considers a scenario in which (i) each agent may observe their own actions, but
may not directly observe the actions of others, and (ii) agents have some
uncertainty about the underlying state of the world. In order for an agent to
obtain information pertaining to the action history of another, the information
must be disseminated through a (possibly sparse) overlaid communication
infrastructure. In order to learn pure-strategy NE in this setting, the paper
studies a general class of learning dynamics based on the Fictitious Play (FP)
algorithm which we refer to as inertial best response dynamics. As an
application of this general result, the paper subsequently studies distributed
implementations of the classical FP algorithm (with inertia), and the Joint
Strategy FP (JSFP) algorithm (with inertia) in the above setting. Finally,
numerical simulations are provided which verify the findings. | | Source: | arXiv, 1605.0601 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
|
| |
|
|
|
REGISTER