On Scheduling a Photolithograhy Toolset Based on a Deep Reinforcement Learning Approach with Action Filter.
Taehyung KimHyeong-Ook KimTae-Eog LeeJames Robert MorrisonEungjin KimPublished in: WSC (2021)
Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- action space
- scheduling problem
- function approximation
- reward shaping
- state action
- transition model
- scheduling algorithm
- state space
- round robin
- markov decision processes
- temporal difference
- dynamic programming
- agent learns
- continuous state
- real time database systems
- fitted q iteration
- machine learning
- filtering algorithm
- parallel machines
- resource allocation
- learning process
- multi agent
- information systems
- development process
- sensory inputs
- optimal policy
- optimal solution
- learning algorithm