Code Monkey home page Code Monkey logo

dcc-env's Introduction

DCC-Env

This is an environment for use with Veins-Gym. The scenario uses DCC, the aim is to learn optimal parameters. For this, the observations are the average channel busy time, reward is a metric derived from the vehicles' age of information, and the action are the CBR values used by DCC for its transition.

Initial steps:

  • install dependencies of the simulation: SUMO (v1.6.0) and OMNeT++ (v5.6.*), such that you can run Veins (v5.1, bundled with veins-gym)
  • install the dependencies listed in requirements.txt
  • build the simulation: snakemake -jall
  • and run the example: agents/trivial.py.

For a deeper look into the simulation, see its configuration (scenario), and the GymConnection class.

Further Notes

Check out veins-gym, which serves as a foundation for this work. The veins-gym repository also contains a Dockerfile that can be used to build a containerized environment to run the DCC-Env in.

dcc-env's People

Contributors

dbuse avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

dcc-env's Issues

snakemake error

Hello All,

Whenever I run snakemake -jall to compile, I get the below error:

WorkflowError in line 18 of /home/suv2hi/Downloads/dcc-env-master/Snakefile:
Extensions for multiext may not contain path delimiters (/,) and must start with '.' (e.g. .txt).
File "/home/suv2hi/Downloads/dcc-env-master/Snakefile", line 18, in

Kindly advise how to resolve it.

Omnet 5.6.2
Sumo 1.12.0

Value Error

Dear @dbuse
When I try to build a model on DCC like below:

`def build_model(states, actions):

model = tensorflow.keras.Sequential()  

model.add(tensorflow.keras.layers.Reshape((1,), input_shape=(1,)))
#model.add(Flatten(input_shape=(1,)))

model.add(Dense(24, activation='relu', input_shape=(1,)))

model.add(Dense(24, activation='relu'))

model.add(Dense(actions, activation='linear'))
#model.add(Flatten(input_shape=(states,1)))
print("model.output_shape",model.output_shape)
print("model.input_shape",model.input_shape)

return model`

I got an error as:

ValueError: Error when checking input: expected reshape_input to have 2 dimensions, but got array with shape (1, 1, 1)

And then got this error:

Error: tcpip::Socket::recvAndCheck @ recv: peer shutdown Quitting (on error). malloc_consolidate(): unaligned fastbin chunk detected Aborted (core dumped)

Especially, for the ValueError I nearly spent 1 month and got no progress.
What should I do?
Regards,
Sorry for disturbing

Better reward function

The current reward function results in only low differences between different behaviors.

Probably the period of time for which we look back for neighbor updates is too long.

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.