marmotlab / scrimp Goto Github PK
View Code? Open in Web Editor NEWoffical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'
License: MIT License
offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'
License: MIT License
I‘m sorry to disturb you in your busy schedule. But when I run python3 setup.py build_ext --inplace, there is the following error:
mstar_type_defs.hpp:8:10: fatal error: boost/graph/graph_traits.hpp: No such file or directory
8 | #include <boost/graph/graph_traits.hpp>
So I installed Boost=1.76.0,and finished compiling. However, when I run python3 and import cpp_mstar, the following error occurred:
Traceback (most recent call last):
File "", line 1, in
ModuleNotFoundError: No module named 'cpp_mstar'
How to solve this problem?
Thanks for your kindness.
Hello!
First off, thank you for your work on the SCRIMP paper. It presents an intriguing approach to the challenges problem.
One aspect I'm curious about is how SCRIMP handles potential collisions with a very restricted 3x3 FOV. To paint a picture, consider a scenario where two agents (agents A [moving right] and B [moving left]) are in a narrow corridor with just a single cell between them, such that they're outside each other's FOVs:
#####
.A.B.
#####
Given their limited visibility, how does the system ensure these agents avoid collisions in real-time? Does the global communication mechanism based on the modified transformer help in such close-quartered scenarios, or are there other components of the system that play a role in avoiding potential conflicts in such situations?
The repo requires python 3.7 but it seems NetworkX 2.8.8 and pyglet 2.0.9 (what got installed automatically as a dependency of gym I assume) both require python 3.8. I fixed the networkx issue by installing 2.6.3 but then when I run driver.py I run into the pyglet error which stems from gym's rendering module:
(myvenv) ~/SCRIMP
n-62-30-5(s222376) $ python3 driver.py
Traceback (most recent call last):
File "driver.py", line 13, in <module>
from mapf_gym import MAPFEnv
File "SCRIMP/mapf_gym.py", line 11, in <module>
from gym.envs.classic_control import rendering
File "SCRIMP/myvenv/lib/python3.7/site-packages/gym/envs/classic_control/rendering.py", line 18, in <module>
import pyglet
File "SCRIMP/myvenv/lib/python3.7/site-packages/pyglet/__init__.py", line 19, in <module>
raise Exception(f"pyglet {version} requires Python {MIN_PYTHON_VERSION_STR} or newer.")
Exception: pyglet 2.0.9 requires Python 3.8 or newer.
I tried pyglet 2.0.0 which docs say can use 3.7 but the 3.8 error still arose. I then tried pyglet 1.5.27 but then ran into another error on import:
raise NoSuchDisplayException('Cannot connect to "%s"' % name)
pyglet.canvas.xlib.NoSuchDisplayException: Cannot connect to "None"
Any suggestions? Should I just upgrade to python 3.8?
Running this on:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Model name: Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz
Also, I know it's a bit inconvenient, but maybe you all could make a docker image for people to download to avoid fighting all these dependency issues? Makes things much faster for those that want to run/modify your code :)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.