Completing the training of a pre-trained model.

reiniscimurs / DRL-robot-navigation

Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.

MIT License

486 stars 97 forks source link

Completing the training of a pre-trained model. #140

Open iAmSarahAllam opened 2 months ago

iAmSarahAllam commented 2 months ago

Hi,

I was wondering if I can complete the training on a per-trained model that I stopped. If yes how can I do that?

bb0928 commented 2 months ago

I am wondering the same question

reiniscimurs commented 2 months ago

You can load the weights from a previously trained model with the load function: https://github.com/reiniscimurs/DRL-robot-navigation/blob/main/TD3/train_velodyne_td3.py#L210

See test_velodyne_td3.py for the implementation: https://github.com/reiniscimurs/DRL-robot-navigation/blob/main/TD3/test_velodyne_td3.py#L63-L67