Distributed multi-agent optimization with state-dependent communication.
Ilan LobelAsuman E. OzdaglarDiego FeijerPublished in: Math. Program. (2011)
Keyphrases
- multi agent
- state dependent
- steady state
- agent communication
- flow control
- communication overhead
- communication cost
- optimal policy
- queueing networks
- product form
- queue length
- multi agent systems
- reinforcement learning
- intelligent agents
- single server
- arrival rate
- service rates
- multiagent systems
- markov chain
- long run
- asymptotically optimal
- distributed systems
- state space
- customer demand
- special case
- machine learning
- neural network