An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents.
Marta MonaciValerio AgasucciGiorgio GraniPublished in: Eur. J. Oper. Res. (2024)
Keyphrases
- job shop scheduling problem
- actor critic
- dynamic programming
- memetic algorithm
- benchmark problems
- optimization algorithm
- optimal solution
- multi agent systems
- cost function
- simulated annealing
- policy gradient
- gradient method
- np hard
- search space
- computational complexity
- objective function
- similarity measure
- average reward
- k means
- multi agent
- genetic algorithm
- learning algorithm
- policy iteration
- action selection
- reinforcement learning
- optimal control
- knapsack problem
- combinatorial optimization
- tabu search
- optimal policy
- neural network
- evolutionary algorithm