A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.
Clone or download
jal278 Merge pull request #3 from VashishtMadhavan/master
adding bootstrap + css formatting to video HTML files
Latest commit 58e5e8e Jan 10, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
atari_zoo Modify function to return image Jan 5, 2019
colab Adding colaboratory demo Jan 5, 2019
dimensionality_reduction modified README Dec 1, 2018
docs adding bootstrap + css formatting to video HTML files Jan 9, 2019
examples Initial commit Nov 29, 2018
notebooks Initial commit Nov 29, 2018
.gitignore Initial commit Nov 29, 2018
LICENSE Initial commit Nov 29, 2018
NOTICE Initial commit Nov 29, 2018
README.md Added link to colab Jan 5, 2019
setup.py Initial commit Nov 29, 2018

README.md

Atari Zoo

The aim of this project is to disseminate deep reinforcement learning agents trained by a variety of algorithms, and to enable easy analysis, comparision, and visualization of them. The hope is to reduce friction for further research into understanding reinforcement learning agents. This project makes use of the excellent Lucid neural network visualization library, and integrates with the Dopamine model release.

A paper introducing this work was published at the Deep RL workshop at NeurIPS 2018: An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents.

About

This software package is accompanied by a binary release of (1) frozen models trained on Atari games by a variety of deep reinforcement learning methods, and (2) cached gameplay experience of those agents in their training environments, which is hosted online.

Installation and Setup

Dependencies:

To install, run setup.py install after installing dependencies.

Examples

import atari_zoo
from atari_zoo import MakeAtariModel
from pylab import *

algo = "a2c"
env = "ZaxxonNoFrameskip-v4"
run_id = 1
tag = "final"
m = MakeAtariModel(algo,env,run_id,tag)()

# get observations, frames, and ram state from a representative rollout
obs = m.get_observations()
frames = m.get_frames()
ram = m.get_ram()

# visualize first layer of convolutional weights
session = atari_zoo.utils.get_session()

m.load_graphdef()
m.import_graph()

conv_weights = m.get_weights(session,0)
atari_zoo.utils.visualize_conv_w(conv_weights)
show()

From the command line you can run: python -m atari_zoo.activation_movie --algo rainbow --environment PongNoFrameskip-v4 --run_id 1 --output ./pong_rainbow1_activation.mp4

Notebooks

Example jupyter notebooks live in the notebook directory that give further examples of how this library can be used.

A starter colab notebook enables you to check out the library without downloading and installing it.

Web tools

Source code for training algorithms that produced zoo models

We trained four algorithms ourselves:

We took trained final models from two algorithms (DQN and Rainbow) from the Dopamine model release:

Citation

To cite this work in publications, please use the following BibTex entry:

@inproceedings{
title = {An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents},
author = {Felipe Such, Vashish Madhavan, Rosanne Liu, Rui Wang, Pablo Castro, Yulun Li, Ludwig Schubert, Marc Bellemare, Jeff Clune, Joel Lehman},
booktitle = {Proceedings of the Deep RL Workshop at NeurIPS 2018},
year = {2018},
}

Contact Information

For questions, comments, and suggestions, email joel.lehman@uber.com.