search

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

How should I evaluate the training situation? #144

Open pihkhggc opened 1 month ago

pihkhggc commented 1 month ago

How should I evaluate the training situation? What do these three curves represent and what information can I read

Screenshot 2024-05-16 at 08-52-57 TensorBoard Screenshot 2024-05-16 at 08-53-11 TensorBoard Screenshot 2024-05-16 at 08-56-32 TensorBoard

reiniscimurs commented 1 month ago

You can see some discussion on that here: https://github.com/reiniscimurs/DRL-robot-navigation/issues/103