Revising the Observation Satellite Scheduling Problem Based on Deep Reinforcement Learning.
Yixin HuangZhongcheng MuShufan WuBenjie CuiYuxiao DuanPublished in: Remote. Sens. (2021)
Keyphrases
- scheduling problem
- reinforcement learning
- single machine
- flowshop
- permutation flowshop
- np hard
- setup times
- precedence constraints
- function approximation
- tabu search
- processing times
- minimizing makespan
- optimal policy
- remote sensing
- reinforcement learning algorithms
- belief revision
- multi agent reinforcement learning
- total tardiness
- unrelated parallel machines
- earliness tardiness
- machine learning
- parallel machines
- temporal difference
- dynamic programming
- learning algorithm
- robotic control
- long run
- action selection
- deep learning
- transfer learning
- simulated annealing
- supply chain
- policy search
- search algorithm
- optimal solution
- neural network