Multi-agent deep reinforcement learning based Predictive Maintenance on parallel machines.
Marcelo Luis Ruiz RodríguezSylvain KublerAndrea de GiorgioMaxime CordyJérémy RobertYves Le TraonPublished in: Robotics Comput. Integr. Manuf. (2022)
Keyphrases
- parallel machines
- reinforcement learning
- multi agent
- scheduling problem
- total tardiness
- unrelated parallel machines
- sequence dependent setup times
- massively parallel
- scheduling jobs
- learning agents
- state space
- precedence constraints
- multi agent environments
- release dates
- parallel computing
- setup times
- weighted tardiness
- minimize total
- single agent
- shared memory
- reinforcement learning agents
- optimal policy
- flowshop
- single machine
- learning algorithm
- markov decision processes
- single server
- objective function
- computing systems
- lot sizing
- utility function