In this repository control of inverse pendel has been implemented
-
Install the requirements.txt with ' pip install requirments.txt '
-
the settings of the training can be changed in config.py
-
navigate to /Q-learning for training run: 'python main.py -t' after this a .npy file with the Q-table will be saved under weights
-
The Q-table can be used to visualize the control via 'python main.py'
The space-state of the cartpole was implemented in this repository: https://github.com/openai/gym/blob/master/gym/envs/classic_control/cartpole.py
- Impalement DQN
- Impalement DDQN
- Danikhani
This project is licensed under the MIT License