On some algorithms for limiting average Markov decision processes.
Cherki DaouiMohammed AbbadPublished in: Oper. Res. Lett. (2007)
Keyphrases
- markov decision processes
- policy iteration
- factored mdps
- reachability analysis
- reinforcement learning
- state space
- finite state
- optimal policy
- learning algorithm
- reinforcement learning algorithms
- average cost
- model based reinforcement learning
- transition matrices
- model checking
- linear programming
- partially observable markov decision processes
- computational complexity
- planning under uncertainty
- multi agent
- machine learning