A model-based deep reinforcement learning approach to the nonblocking coordination of modular supervisors of discrete event systems.
Junjun YangKaige TanLei FengZhiwu LiPublished in: Inf. Sci. (2023)
Keyphrases
- discrete event systems
- reinforcement learning
- multi agent reinforcement learning
- model free
- petri net
- complex systems
- telecommunication networks
- model based diagnosis
- multi agent
- failure diagnosis
- timed petri nets
- multiagent learning
- discrete event
- temporal constraints
- multi agent systems
- state space
- cooperative
- function approximation
- reinforcement learning algorithms
- multiagent systems
- mathematical model
- optimal policy
- transfer learning
- simulation model
- context aware
- dynamic programming
- special case