Sir, could you provide a trained model? please

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

636 stars 126 forks source link

Sir, could you provide a trained model? please #161

Open zcjiyouxiusa opened 1 month ago

zcjiyouxiusa commented 1 month ago

hello, sir！I have some trouble with training. why it is hard to train a well model with you origin code. I have run the train_velodyne_td3.py for a half of day with nvidia GPU: RTX 3060. but the robot still can not navigate to its goal. can you tell me how long to run to get a well model. the following pic is the loss and Q value, The loss fluctuates greatly. Is this normal? Snipaste_2024-10-24_14-27-37 Snipaste_2024-10-24_14-27-46 Please help me ! Thanks !

reiniscimurs commented 1 month ago

Hi, please use issue template to submit your issue.