search

Acmece / rl-collision-avoidance

Implementation of the paper "Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning"
https://arxiv.org/abs/1709.10082
326 stars 92 forks source link

Query on stage1_1.pth #16

Open weihan08 opened 3 years ago

weihan08 commented 3 years ago

Hello,

Could you please explain the difference between loading the policy of stage1_1.pth and no policy at all? Is the stage1_1.pth some form of supervised learning?

Acmece commented 3 years ago

Hi, the model in the policy fold is what I have trained. If you want to train from the scratch, you may run the following to trian the stage 1:

rosrun stage_ros_add_pose_and_crash stageros -g worlds/stage1.world
mpiexec -np 24 python ppo_stage1.py

then modify this line to load the policy of stage 1 and train stage2 afterwards:

rosrun stage_ros_add_pose_and_crash stageros -g worlds/stage2.world
mpiexec -np 44 python ppo_stage2.py