Jointly optimal policies for pavement maintenance, resurfacing and reconstruction.
Jinwoo LeeSamer M. MadanatPublished in: EURO J. Transp. Logist. (2015)
Keyphrases
- optimal policy
- markov decision processes
- decision problems
- dynamic programming
- state space
- reinforcement learning
- finite horizon
- infinite horizon
- multistage
- dynamic programming algorithms
- finite state
- serial inventory systems
- state dependent
- sufficient conditions
- long run
- average reward
- markov decision process
- control policies
- average reward reinforcement learning
- average cost
- initial state
- partially observable markov decision processes
- policy iteration
- bayesian reinforcement learning
- reinforcement learning algorithms
- markov decision problems
- production system