https://github.com/google-research/football

Check out the new game server:

Keywords

reinforcement-learning reinforcement-learning-environments

Keywords from Contributors

distributed deep-neural-networks

Last synced: 6 months ago · JSON representation

Repository

Check out the new game server:

Basic Info

Host: GitHub
Owner: google-research
License: apache-2.0
Language: Python
Default Branch: master
Homepage: https://research-football.dev
Size: 26.5 MB

Statistics

Stars: 3,490
Watchers: 92
Forks: 1,326
Open Issues: 80
Releases: 11

Topics

reinforcement-learning reinforcement-learning-environments

Created almost 7 years ago · Last pushed 10 months ago

Metadata Files

Readme Changelog Contributing License

Google Research Football

This repository contains an RL environment based on open-source game Gameplay Football.
It was created by the Google Brain team for research purposes.

Useful links:

Run in Colab - start training in less that 2 minutes.
Google Research Football Paper
GoogleAI blog post
Google Research Football on Cloud
GRF Kaggle competition - take part in the competition playing games against others, win prizes and become the GRF Champion!

We'd like to thank Bastiaan Konings Schuiling, who authored and open-sourced the original version of this game.

Quick Start

In colab

Open our example Colab, that will allow you to start training your model in less than 2 minutes.

This method doesn't support game rendering on screen - if you want to see the game running, please use the method below.

Using Docker

This is the recommended way for Linux-based systems to avoid incompatible package versions. Instructions are available here.

On your computer

1. Install required packages

Linux

```shell sudo apt-get install git cmake build-essential libgl1-mesa-dev libsdl2-dev \ libsdl2-image-dev libsdl2-ttf-dev libsdl2-gfx-dev libboost-all-dev \ libdirectfb-dev libst-dev mesa-utils xvfb x11vnc python3-pip

python3 -m pip install --upgrade pip setuptools psutil wheel ```

macOS

First install brew. It should automatically install Command Line Tools. Next install required packages:

```shell brew install git python3 cmake sdl2 sdl2image sdl2ttf sdl2_gfx boost boost-python3

python3 -m pip install --upgrade pip setuptools psutil wheel ```

Windows

Install Git and Python 3. Update pip in the Command Line (here and for the next steps type python instead of python3) commandline python -m pip install --upgrade pip setuptools psutil wheel

2. Install GFootball

Option a. From PyPi package (recommended)

shell python3 -m pip install gfootball

Option b. Installing from sources using GitHub repository

(On Windows you have to install additional tools and set an environment variable, see Compiling Engine for detailed instructions.)

shell git clone https://github.com/google-research/football.git cd football

Optionally you can use virtual environment:

shell python3 -m venv football-env source football-env/bin/activate

Next, build the game engine and install dependencies:

shell python3 -m pip install . This command can run for a couple of minutes, as it compiles the C++ environment in the background. If you face any problems, first check Compiling Engine documentation and search GitHub issues.

3. Time to play!

shell python3 -m gfootball.play_game --action_set=full Make sure to check out the keyboard mappings. To quit the game press Ctrl+C in the terminal.

Update PIP, so that tensorflow 1.15 is available: python3 -m pip install --upgrade pip setuptools wheel
TensorFlow: python3 -m pip install tensorflow==1.15.* or python3 -m pip install tensorflow-gpu==1.15.*, depending on whether you want CPU or GPU version;
Sonnet and psutil: python3 -m pip install dm-sonnet==1.* psutil;
OpenAI Baselines: python3 -m pip install git+https://github.com/openai/baselines.git@master.

Then:

To run example PPO experiment on academy_empty_goal scenario, run python3 -m gfootball.examples.run_ppo2 --level=academy_empty_goal_close
To run on academy_pass_and_shoot_with_keeper scenario, run python3 -m gfootball.examples.run_ppo2 --level=academy_pass_and_shoot_with_keeper

In order to train with nice replays being saved, run python3 -m gfootball.examples.run_ppo2 --dump_full_episodes=True --render=True

In order to reproduce PPO results from the paper, please refer to:

gfootball/examples/reprocheckpointeasy.sh
gfootball/examples/reproscoringeasy.sh

Playing the game

Please note that playing the game is implemented through an environment, so human-controlled players use the same interface as the agents. One important implication is that there is a single action per 100 ms reported to the environment, which might cause a lag effect when playing.

Keyboard mappings

The game defines following keyboard mapping (for the keyboard player type):

ARROW UP - run to the top.
ARROW DOWN - run to the bottom.
ARROW LEFT - run to the left.
ARROW RIGHT - run to the right.
S - short pass in the attack mode, pressure in the defense mode.
A - high pass in the attack mode, sliding in the defense mode.
D - shot in the attack mode, team pressure in the defense mode.
W - long pass in the attack mode, goalkeeper pressure in the defense mode.
Q - switch the active player in the defense mode.
C - dribble in the attack mode.
E - sprint.

Play vs built-in AI

Run python3 -m gfootball.play_game --action_set=full. By default, it starts the base scenario and the left player is controlled by the keyboard. Different types of players are supported (gamepad, external bots, agents...). For possible options run python3 -m gfootball.play_game -helpfull.

Play vs pre-trained agent

In particular, one can play against agent trained with run_ppo2 script with the following command (notice no actionset flag, as PPO agent uses default action set): `python3 -m gfootball.playgame --players "keyboard:leftplayers=1;ppo2cnn:rightplayers=1,checkpoint=$YOURPATH"`

Trained checkpoints

We provide trained PPO checkpoints for the following scenarios:

In order to see the checkpoints playing, run python3 -m gfootball.play_game --players "ppo2_cnn:left_players=1,policy=gfootball_impala_cnn,checkpoint=$CHECKPOINT" --level=$LEVEL, where $CHECKPOINT is the path to downloaded checkpoint. Please note that the checkpoints were trained with Tensorflow 1.15 version. Using different Tensorflow version may result in errors. The easiest way to run these checkpoints is through provided Dockerfile_examples image. See running in docker for details (just override the default Docker definition with -f Dockerfile_examples parameter).

In order to train against a checkpoint, you can pass 'extraplayers' argument to createenvironment function. For example extraplayers='ppo2cnn:rightplayers=1,policy=gfootballimpala_cnn,checkpoint=$CHECKPOINT'.

Owner

Name: Google Research
Login: google-research
Kind: organization
Location: Earth

Website: https://research.google
Repositories: 226
Profile: https://github.com/google-research

GitHub Events

Total

Issues event: 16
Watch event: 168
Issue comment event: 25
Push event: 1
Pull request review event: 1
Fork event: 67

Last Year

Issues event: 16
Watch event: 167
Issue comment event: 25
Push event: 1
Pull request review event: 1
Fork event: 67

Committers

Last synced: 6 months ago

All Time

Total Commits: 78
Total Committers: 24
Avg Commits per committer: 3.25
Development Distribution Score (DDS): 0.59

Past Year

Commits: 1
Committers: 1
Avg Commits per committer: 1.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Piotr Stanczyk	s**k@g**m	32
Victor Khaustov	3**r@u**m	15
Google Research Football Team	n**y@g**m	5
Anton Raichuk	r**n@g**m	3
Konrad Staniszewski	C**d@u**m	2
Pratik Raj	R**1@g**m	2
Witalis Domitrz	w**z@g**m	2
AntonRaichuk	4**k@u**m	1
Avik Jain	a**k@a**e	1
Ayoub Kachkach	A**h@g**m	1
DCorneal	4**l@u**m	1
Frank Budrowski	3**i@u**m	1
Joy Banerjee	3**8@u**m	1
Karol Kurach	k**h@g**m	1
Sahil Rajput	s**6@g**m	1
Sean McGuire	m**5@s**u	1
Thomas Tumiel	t**l@g**m	1
Yoanis Gil Delgado	y**l@u**m	1
arfy slowy	s**y@g**m	1
boscotsang	b**3@g**m	1
dongr0510	5**0@u**m	1
keshavgbpecdelhi	5**i@u**m	1
pkozakowski	5**i@u**m	1
qstanczyk	5**k@u**m	1

Committer Domains (Top 20 + Academic)

google.com: 4 students.rowan.edu: 1 avikjain.me: 1

Issues and Pull Requests

Last synced: 7 months ago

All Time

Total issues: 121
Total pull requests: 23
Average time to close issues: 6 months
Average time to close pull requests: 15 days
Total issue authors: 107
Total pull request authors: 12
Average comments per issue: 2.4
Average comments per pull request: 1.48
Merged pull requests: 11
Bot issues: 0
Bot pull requests: 1

Past Year

Issues: 12
Pull requests: 0
Average time to close issues: about 2 months
Average time to close pull requests: N/A
Issue authors: 12
Pull request authors: 0
Average comments per issue: 1.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

jecompton (3)
Chen001117 (3)
fighting-zz (3)
CarlossShi (2)
chrisyrniu (2)
fspinola (2)
artinisenaj2014 (2)
opocaj92 (2)
OrilinZ (2)
maximfedorchak1 (2)
kakuhin1984 (2)
tianyma (1)
huangshiyu13 (1)
SakuragiJump (1)
48223050 (1)

Pull Request Authors

vi3itor (10)
dennisagb (2)
agurodriguez (2)
ymetz (1)
Letschi6 (1)
rahimrahimovv (1)
MatthiasPrall (1)
dependabot[bot] (1)
orkhanjamalov1991 (1)
slowy07 (1)
ikertejero (1)
cyfra (1)

Top Labels

Issue Labels

Pull Request Labels

cla: yes (9) cla: no (3) dependencies (1)

Packages

Total packages: 2
Total downloads:
- pypi 753 last-month
Total docker downloads: 36

Total dependent packages: 1
(may contain duplicates)
Total dependent repositories: 57
(may contain duplicates)
Total versions: 30
Total maintainers: 2

pypi.org: gfootball

Google Research Football - RL environment based on open-source game Gameplay Football

Homepage: https://github.com/google-research/football
Documentation: https://gfootball.readthedocs.io/
License: Apache 2.0
Latest release: 2.10.2
published about 4 years ago

Versions: 27
Dependent Packages: 1
Dependent Repositories: 57
Downloads: 753 Last month
Docker Downloads: 36

Rankings

Forks count: 1.2%

Stargazers count: 1.4%

Dependent repos count: 2.0%

Average: 3.8%

Docker downloads count: 3.9%

Dependent packages count: 4.7%

Downloads: 9.6%

Maintainers (2)

google_opensource gfootball

Last synced: 6 months ago

proxy.golang.org: github.com/google-research/football

Documentation: https://pkg.go.dev/github.com/google-research/football#section-documentation
License: apache-2.0
Latest release: v2.10.2+incompatible
published about 4 years ago

Versions: 3
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 6.9%

Last synced: 6 months ago

https://github.com/google-research/football

Science Score: 33.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Google Research Football

Quick Start

In colab

Using Docker

On your computer

1. Install required packages

Linux

macOS

Windows

2. Install GFootball

Option a. From PyPi package (recommended)

Option b. Installing from sources using GitHub repository

3. Time to play!

Contents

Training agents to play GRF

Run training

Playing the game

Keyboard mappings

Play vs built-in AI

Play vs pre-trained agent

Trained checkpoints

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: gfootball

Rankings

Maintainers (2)

proxy.golang.org: github.com/google-research/football

Rankings