Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs (Extended Version).
Philipp RobbelFrans A. OliehoekMykel J. KochenderferPublished in: CoRR (2015)
Keyphrases
- linear programming
- multi agent
- markov decision problems
- markov decision processes
- dynamic programming
- dec pomdps
- planning under uncertainty
- factored mdps
- linear program
- reinforcement learning
- multiagent systems
- cooperative
- average cost
- factored markov decision processes
- single agent
- state space
- optimal solution
- primal dual
- intelligent agents
- column generation
- policy evaluation
- exact solution
- multi agent systems
- multiple agents
- quadratic programming
- finite number