Application of multi-agent Markov decision processes to gate assignment problem.
Oussama AounAbdellatif El AfiaPublished in: CIST (2014)
Keyphrases
- markov decision processes
- reinforcement learning
- multi agent
- state space
- optimal policy
- finite state
- planning under uncertainty
- transition matrices
- finite horizon
- reinforcement learning algorithms
- policy iteration
- infinite horizon
- average reward
- partially observable
- dynamic programming
- decision theoretic planning
- reachability analysis
- decision problems
- stochastic games
- factored mdps
- multi agent systems