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
483 stars 97 forks source link

Errors when I start the training, #64

Closed Talha771 closed 7 months ago

Talha771 commented 1 year ago

When I start the training, it sets everything up, but then asks prints [ERROR] [1687396711.914794882, 218.094000000]: Updating ModelState: model [cardboard_box_0] does not exist [ERROR] [1687396711.914858032, 218.094000000]: Updating ModelState: model [cardboard_box_1] does not exist [ERROR] [1687396711.914871440, 218.094000000]: Updating ModelState: model [cardboard_box_2] does not exist [ERROR] [1687396711.914885786, 218.094000000]: Updating ModelState: model [cardboard_box_3] does not exist

over and over again and makes no progress

reiniscimurs commented 1 year ago

This usually happens when the resources are not set up properly. Please take a look in https://github.com/reiniscimurs/DRL-robot-navigation/issues/44, https://github.com/reiniscimurs/DRL-robot-navigation/issues/30, https://github.com/reiniscimurs/DRL-robot-navigation/issues/16#issue-1215832058 and resource path setting description in https://medium.com/@reinis_86651/deep-reinforcement-learning-in-mobile-robot-navigation-tutorial-part1-installation-d62715722303

That most likely should solve your problem