Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs.
Philipp RobbelFrans A. OliehoekMykel J. KochenderferPublished in: AAAI (2016)
Keyphrases
- linear programming
- multi agent
- markov decision problems
- factored mdps
- dec pomdps
- markov decision processes
- dynamic programming
- planning under uncertainty
- linear program
- reinforcement learning
- multiagent systems
- np hard
- average cost
- optimal solution
- policy iteration
- autonomous agents
- factored markov decision processes
- policy evaluation
- decision theoretic planning
- cooperative
- quality guarantees
- single agent
- primal dual
- decision theoretic
- special case
- optimal policy
- state space
- objective function
- infinite horizon
- multi agent systems
- context specific
- quadratic programming
- efficient computation
- constraint propagation
- intelligent agents
- markov chain