Coder Social home page Coder Social logo

paper-ml-agents's Introduction

papers-ml-agents

This repository is meant to offer a way to reproduce the experiments of some of the papers Unity published using ML-Agents.

MA-POCA

Multi-Agent POsthumous Credit Assignment (MA-POCA) is a multi-agent learning algorithm that can gracefully deal with spawning and despawning agents without the use of absorbing states. See here for more information.

paper-ml-agents's People

Contributors

repodb[bot] avatar vincentpierre avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

paper-ml-agents's Issues

Independent actors configuration

Hi, I want to know if there's any setting in POCA where each agent in a team gets a separate policy with a separate neural network. Can I change any parameters in the configuration yaml file

HTTP Error Launching poca environment

Hi There,

I'm seeing the Unity Splash Screen and have followed the install and run instructions as best as I can tell. I'm running into an error where it seems to be trying to connect to a URL which no longer exists. Am I missing something or should I be running differently?

Version information:
ml-agents: 0.1,
ml-agents-envs: 0.27.0,
Communicator API: 1.5.0,
PyTorch: 2.0.0+cpu
[WARNING] Attempt 1 / 5: Failed to download and extract binary.
[WARNING] Attempt 2 / 5: Failed to download and extract binary.
[WARNING] Attempt 3 / 5: Failed to download and extract binary.
[WARNING] Attempt 4 / 5: Failed to download and extract binary.
[ERROR] UnityEnvironment worker 0: environment raised an unexpected exception.
Traceback (most recent call last):
File "d:\development\paper-ml-agents-main\paper-ml-agents-main\ma-poca\mapoca\mapoca\trainers\subprocess_env_manager.py", line 160, in worker
env = env_factory(worker_id, side_channels)
File "d:\development\paper-ml-agents-main\paper-ml-agents-main\ma-poca\mapoca\mapoca\trainers\learn.py", line 174, in create_unity_environment
return mapoca_registry[env_name].make(
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\remote_registry_entry.py", line 61, in make
path = get_local_binary_path(self.identifier, url)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\binary_utils.py", line 40, in get_local_binary_path
download_and_extract_zip(url, name)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\binary_utils.py", line 131, in download_and_extract_zip
request = urllib.request.urlopen(url, timeout=30)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 214, in urlopen
return opener.open(url, data, timeout)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 523, in open
response = meth(req, response)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 632, in http_response
response = self.parent.error(
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 561, in error
return self._call_chain(*args)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 494, in _call_chain
result = func(*args)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 641, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found https://storage.googleapis.com/mlagents-test-environments/ma-poca/win/Startup.zip
[INFO] Learning was interrupted. Please wait while the graph is generated.
Traceback (most recent call last):
File "D:\Downloads\anaconda3\envs\mlagents20\lib\multiprocessing\queues.py", line 245, in _feed
obj = _ForkingPickler.dumps(obj)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\multiprocessing\reduction.py", line 51, in dumps
cls(buf, protocol).dump(obj)
TypeError: cannot pickle '_io.BufferedReader' object
Process Process-1:
Traceback (most recent call last):
File "d:\development\paper-ml-agents-main\paper-ml-agents-main\ma-poca\mapoca\mapoca\trainers\subprocess_env_manager.py", line 160, in worker
env = env_factory(worker_id, side_channels)
File "d:\development\paper-ml-agents-main\paper-ml-agents-main\ma-poca\mapoca\mapoca\trainers\learn.py", line 174, in create_unity_environment
return mapoca_registry[env_name].make(
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\remote_registry_entry.py", line 61, in make
path = get_local_binary_path(self.identifier, url)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\binary_utils.py", line 40, in get_local_binary_path
download_and_extract_zip(url, name)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\site-packages\mlagents_envs\registry\binary_utils.py", line 131, in download_and_extract_zip
request = urllib.request.urlopen(url, timeout=30)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 214, in urlopen
return opener.open(url, data, timeout)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 523, in open
response = meth(req, response)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 632, in http_response
response = self.parent.error(
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 561, in error
return self._call_chain(*args)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 494, in _call_chain
result = func(*args)
File "D:\Downloads\anaconda3\envs\mlagents20\lib\urllib\request.py", line 641, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found https://storage.googleapis.com/mlagents-test-environments/ma-poca/win/Startup.zip

Thanks,
Ram

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.