Modelling of hydrological persistence for hidden state Markov decision processes.
Aiden FisherDavid GreenAndrew MetcalfePublished in: Ann. Oper. Res. (2012)
Keyphrases
- markov decision processes
- hidden state
- partially observable
- reinforcement learning
- state space
- partially observable markov decision processes
- optimal policy
- finite state
- hidden markov models
- markov models
- dynamic programming
- dynamical systems
- policy iteration
- planning under uncertainty
- decision theoretic planning
- infinite horizon
- average reward
- average cost
- fully observable
- reward function
- data mining
- markov decision process
- markov decision problems
- transition matrices
- decision processes
- action space
- learning algorithm
- decentralized control
- temporal difference
- objective function