Acmece/rl-collision-avoidance
Implementation of the paper "Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning"
Python
Issues
- 3
About the ERROR: [rospack] Error: package 'stage_ros_add_pose_and_crash' not found
#27 opened by ChaoChen-zhicat - 1
Stage 2 error
#22 opened by Balajinatesan - 2
Segmentation fault
#25 opened by Mealoore - 0
Environment
#29 opened by yangzhongii - 0
visualize
#28 opened by Driedturnip - 0
convergence
#26 opened by Mealoore - 1
Output from training
#24 opened by juliogodoy - 0
Questions about cmdpose tests.py
#23 opened by lcq123-jpg - 6
some question about code
#19 opened by BingHan0458 - 0
Question about ppo algorithm
#21 opened by sinaqahremani - 0
how to dectect crash
#20 opened by wawachen - 3
How to train a new model from scratch to pass the test? Is it sufficient to train in stage 2 only?
#3 opened by chesternimiz - 3
Query on Training the Policy
#15 opened by gwhan98 - 1
Difference between stage1_1.pth and stage1_2.pth
#17 opened by gwhan98 - 1
Why trained policy is not as good as yours
#18 opened by gwhan98 - 1
Query on stage1_1.pth
#16 opened by weihan08 - 5
Segmentation fault (core dumped) problem
#12 opened by CzJaewan - 1
some questions during trainning stage1
#14 opened by HanBing0802 - 1
stage package not found
#11 opened by sundyCoder - 2
dynamic obstacle model
#10 opened by EcustBoy - 2
Hello, can you tell me how the model file "stage2.pth" in your "rl-collision-avoidance" code was trained? Why does the model I trained based on the code you gave use "circle_test.py" to test poorly (because it can't be turned in advance, it causes a collision)?
#9 opened by zhinengshidai - 3
Error compiling code
#7 opened by priyablue - 1
ROS time moved backwards
#8 opened by LanxinL - 1
- 2
- 0
- 3