Policy Iteration Approach to the Infinite Horizon Average Optimal Control of Probabilistic Boolean Networks.
Yuhu WuYuqian GuoMitsuru ToyodaPublished in: IEEE Trans. Neural Networks Learn. Syst. (2021)
Keyphrases
- infinite horizon
- optimal control
- policy iteration
- average cost
- finite horizon
- dynamic programming
- markov decision process
- control strategy
- stochastic demand
- single item
- production planning
- partially observable
- average reward
- reinforcement learning
- holding cost
- probabilistic model
- markov decision processes
- optimal policy
- markov decision problems
- bayesian networks
- initial state
- linear program