A Continuous-Time Markov Decision Process for Infrastructure Surveillance.
Jonathan OttPublished in: OR (2010)
Keyphrases
- markov decision process
- state space
- semi markov decision process
- stationary policies
- markov chain
- markov decision processes
- reinforcement learning
- optimal policy
- finite horizon
- transition probabilities
- infinite horizon
- transition matrices
- optimal control
- dynamic programming
- policy iteration
- dynamical systems
- search space
- real time
- higher order
- belief state
- initial state
- dynamic systems
- partially observable
- state variables
- planning problems
- prior knowledge
- search algorithm
- learning algorithm