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

Segmentation fault (core dumped) problem #12

Closed CzJaewan closed 3 years ago

CzJaewan commented 3 years ago

Hello. In order to learn with two different policies, I opened 2 mpis and tried to learn a total of 7 agents at once.

In the process, a segemtation fault (core dumped) occurs.

Do you know a solution to this?.

Learning proceeds from 300 episodes to 1000 episodes, but an error always occurs after that.

Acmece commented 3 years ago

I have run into the error before. I am sorry to say that I didn't dig into more about it. Hope you can fix it!

George-Chia commented 3 years ago

I met the problem too!

BingHan0458 commented 3 years ago

I met the problem too!

BingHan0458 commented 3 years ago

Hello. In order to learn with two different policies, I opened 2 mpis and tried to learn a total of 7 agents at once.

  • $ rosrun stage_ros_add_pose_and_crash stageros -u /home/nscl/rl_ws/src/RLCA_trainning/worlds/servingbot_agent.world
  • $ mpiexec -np 3 python ppo_stage.py
  • $ mpiexec -np 4 python ppo_stage.py

In the process, a segemtation fault (core dumped) occurs.

  • Segmentation fault (core dumped)

Do you know a solution to this?.

Learning proceeds from 300 episodes to 1000 episodes, but an error always occurs after that.

How did you solve it?

Acmece commented 3 years ago

Pease refer to this issue