Task Scheduling in Assembly Lines with Single-Agent Deep Reinforcement Learning.
Muhammad ImranGiovanni AntonucciAlessandro Di GiorgioFrancesco Delli PriscoliAndrea TortorelliFrancesco LiberatiPublished in: CoDIT (2023)
Keyphrases
- single agent
- reinforcement learning
- assembly line
- multi agent
- assembly line balancing
- multiple agents
- action space
- beam search
- multi agent systems
- processing times
- decision problems
- dynamic environments
- multi agent coordination
- state space
- production line
- manufacturing systems
- learning algorithm
- policy gradient
- precedence constraints
- optimal policy
- learning agent
- supervised learning
- path finding
- orders of magnitude
- branch and bound algorithm
- search strategies
- multiple objectives
- cooperative
- continuous state
- markov decision processes
- optimal solution