An Option and Agent Selection Policy with Logarithmic Regret for Multi Agent Multi Armed Bandit Problems on Random Graphs.
Pathmanathan PankayarajD. H. S. MaithripalaPublished in: CoRR (2019)
Keyphrases
- multi armed bandit problems
- multi agent
- random graphs
- bandit problems
- multi agent systems
- multiagent systems
- multiple agents
- intelligent agents
- autonomous agents
- cooperative agents
- heterogeneous agents
- graph theoretic
- single agent
- cognitive agents
- phase transition
- undirected graph
- reinforcement learning
- power law
- ranking algorithm
- decision problems
- evolutionary algorithm