Digital twin composition in smart manufacturing via Markov decision processes.
Giuseppe De GiacomoMarco FavoritoFrancesco LeottaMassimo MecellaLuciana SiloPublished in: Comput. Ind. (2023)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- policy iteration
- transition matrices
- reinforcement learning
- reachability analysis
- dynamic programming
- decision theoretic planning
- action space
- infinite horizon
- model based reinforcement learning
- factored mdps
- reinforcement learning algorithms
- average reward
- finite horizon
- search algorithm
- partially observable
- decision processes
- markov decision process
- planning under uncertainty
- state and action spaces
- risk sensitive
- state abstraction
- web service composition
- fixed point
- decision problems
- markov chain