A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
| Autor: | Ioannis Ch. Paschalidis, Paris Pennesi |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Adaptive control
Artificial neural network Stochastic process Computer science business.industry Multi-agent system Distributed computing Decision theory Mobile computing Markov process Computer Science Applications Computer Science::Multiagent Systems Dynamic programming symbols.namesake Control and Systems Engineering Distributed algorithm Complete information symbols Reinforcement learning Artificial intelligence Coordination game Electrical and Electronic Engineering business Algorithm Wireless sensor network |
| Zdroj: | IEEE Transactions on Automatic Control. 55:492-497 |
| ISSN: | 1558-2523 0018-9286 |
| DOI: | 10.1109/tac.2009.2037462 |
| Popis: | We introduce and establish the convergence of a distributed actor-critic method that orchestrates the coordination of multiple agents solving a general class of a Markov decision problem. The method leverages the centralized single-agent actor-critic algorithm of and uses a consensus-like algorithm for updating agents' policy parameters. As an application and to validate our approach we consider a reward collection problem as an instance of a multi-agent coordination problem in a partially known environment and subject to dynamical changes and communication constraints. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|