Dynamic volunteer assignment

The following files are included: a2c_algorithm.py (17.1 KB): Python implementation of the Advantage Actor-Critic (A2C) algorithm used for managing multi-class parallel queues. algorithmperformance.zip (28.1 MB): A zipped folder containing performance evaluation data for the various algorithms presented in the paper. ant_colony_optimization.py (5.36 KB): Python implementation of the Ant Colony Optimization algorithm used as a heuristic method in solving the scheduling problem. attention_module.py (6.58 KB): Python code for the attention module used within the deep reinforcement learning framework to enhance model performance. diferrent rules.zip (1.18 MB): A zipped folder with data related to the performance of different scheduling rules and heuristics in managing the multi-class queues. environment.py (5.59 KB): The simulation environment setup, defining the multi-class queueing system and worker service capabilities. genetic_algorithm_optimization.py (5.18 KB): Python implementation of the Genetic Algorithm used as an alternative optimization heuristic. ppo_algorithm.py (18.7 KB): Python implementation of the Proximal Policy Optimization (PPO) algorithm used as a deep reinforcement learning approach for queue management. sensitivity.zip (55 KB): A zipped folder with sensitivity analysis data to evaluate the robustness of the algorithms under various parameter settings. various distribution.zip: A zipped folder containing data for testing the algorithms under various distributions for arrival time .