Percentile queries in multi-dimensional Markov decision processes.
Mickael RandourJean-François RaskinOcan SankurPublished in: Formal Methods Syst. Des. (2017)
Keyphrases
- markov decision processes
- multi dimensional
- range queries
- finite state
- optimal policy
- transition matrices
- state space
- policy iteration
- dynamic programming
- query processing
- finite horizon
- reinforcement learning
- decision processes
- infinite horizon
- action space
- average reward
- factored mdps
- decision theoretic planning
- planning under uncertainty
- average cost
- partially observable
- data cube
- markov decision process
- action sets
- reachability analysis
- semi markov decision processes
- heuristic search
- risk sensitive
- reward function