A New Distributed Constrained Multi-Agent Optimization Protocol with Convergence Proof via Exactness of Penalized Objective Function.
Izumi MasubuchiTakayuki WadaYasumasa FujisakiFabrizio DabbenePublished in: ASCC (2019)
Keyphrases
- multi agent
- convergence proof
- objective function
- optimization problems
- stochastic gradient
- optimization procedure
- multi agent systems
- optimal solution
- least squares
- lower bound
- linear programming
- cost function
- multiple agents
- reinforcement learning
- bregman divergences
- optimization methods
- linear program
- maximum likelihood
- dynamic programming
- mixture model
- single agent
- state space