Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
zoeyuchao authored Mar 4, 2021
1 parent f8f6003 commit 91a72eb
Showing 1 changed file with 2 additions and 1 deletion.
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ This is the source code for RPG (Reward-Randomized Policy Gradient), which is pr
### 1.1 *Agar.io*

<div align=center>![Agar.io](https://github.com/staghuntrpg/agar/tree/main/gif/agar_demo.gif)

[*Agar*](http://en.wikipedia.org/wiki/Agar.io) is a popular multi-player online game. Players control one or more cells in a Petri dish. The goal is to gain as much mass as possible by eating cells smaller than the player's cell while avoiding being eaten by larger ones. Larger cells move slower. Each player starts with one cell but can split a sufficiently large cell into two, allowing them to control multiple cells. The control is performed by mouse motion: all the cells of a player move towards the mouse position.

We transform the Free-For-All (FFA) mode of *Agar* (https://agar.io/) into an Reinforcement Learning (RL) environment and we believe it can be utilized as a new Multi-agent RL testbed for a wide range of problems, such as cooperation, team formation, intention modeling, etc. If you want to use *Agar.io* as your testbed, welcome to visit the agar repository: [https://github.com/staghuntrpg/agar](https://github.com/staghuntrpg/agar).
Expand All @@ -31,4 +32,4 @@ This repository is separated into two folds, GridWorld and Agar, corresponding t

## 3. Publication

If you find this repository useful, please cite our paper: TODO
If you find this repository useful, please cite our paper: TODO

0 comments on commit 91a72eb

Please sign in to comment.