- application of reinforcement learning to optimize transportation routes
- At the beginning, passengers are created with their destination. Elevator knows where passengers want to go even in the other elevators.
- Elevators should transport as many people as possible to their destinations as quickly as possible.
- Reward is a negative value for the sum of people in a building and in elevators.
- PPO + GAE
python main.py
- if you want to change hyper-parameters, you can check "python main.py --help"
- you just train and test basic model using main.py