Optimal control of distributed Markov decision processes with network delays.
Sachin AdlakhaRitesh MadanSanjay LallAndrea J. GoldsmithPublished in: CDC (2007)
Keyphrases
- optimal control
- markov decision processes
- risk sensitive
- dynamic programming
- infinite horizon
- average cost
- policy iteration
- reinforcement learning
- control problems
- state space
- optimal policy
- finite state
- transition matrices
- optimal control problems
- decision theoretic planning
- finite horizon
- partially observable
- multi agent
- reinforcement learning algorithms
- action space
- policy iteration algorithm
- reward function
- decision processes
- control strategy
- np hard
- neural network
- function approximation
- policy gradient
- utility function
- action sets
- multistage
- data mining