maddpg-miniproject's Introduction
1. To run the code, please use the command "./run_training.sh". The bash script cleans up and DELETE previous runs. The script is necessary because we need an extra command to ensure image rendering is possible remotely. Training takes about two hour. If you run locally on your own computer. Be sure to increase the number of parallel agents to the number of cores your computer have in main.py. GPU does not help that much in the computation. 2. To see a visualization of the results, run the script "./run_tensorboard.sh". A link will appear, and direct your browser to that link to see rewards over time and other statistics 3. The trained models are stored in "model_dir" by default. You can also find .gif animations that show how the agents are performing! The gif file contains a grid of separate parallel agents. 4. To understand the goal of the environment: blue dots are the "good agents", and the Red dot is an "adversary". All of the agents' goals are to go near the green target. The blue agents know which one is green, but the Red agent is color-blind and does not know which target is green/black! The optimal solution is for the red agent to chase one of the blue agent, and for the blue agents to split up and go toward each of the target.
maddpg-miniproject's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.