Percentile Queries in Multi-dimensional Markov Decision Processes.
Mickael RandourJean-François RaskinOcan SankurPublished in: CAV (1) (2015)
Keyphrases
- markov decision processes
- multi dimensional
- range queries
- optimal policy
- reinforcement learning
- state space
- finite state
- transition matrices
- policy iteration
- dynamic programming
- query processing
- decision theoretic planning
- reinforcement learning algorithms
- reachability analysis
- average reward
- finite horizon
- action space
- average cost
- model based reinforcement learning
- planning under uncertainty
- action sets
- decision processes
- markov decision process
- state abstraction
- data cube
- factored mdps
- semi markov decision processes
- discounted reward
- risk sensitive
- state and action spaces
- planning problems
- probabilistic planning
- reward function
- partially observable