A Dynamic Programming Algorithm for the Optimal Control of Piecewise Deterministic Markov Processes.
Anthony AlmudevarPublished in: SIAM J. Control. Optim. (2001)
Keyphrases
- optimal control
- markov processes
- markov chain
- markov process
- control problems
- dynamic programming
- stochastic processes
- random fields
- infinite horizon
- control strategy
- queueing systems
- continuous time bayesian networks
- non stationary
- reinforcement learning
- optimal control problems
- continuous time markov chains
- stochastic process
- higher order
- state space
- bayesian networks
- real time