=============

• Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)

• http://www.nature.com/nature/journal/v518/n7540/abs/nature14236.html

• DQN-chainer

• A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012.

• Caffe Model Zoo

• python 2.7

Install Unity experimental-build version:

wget http://download.unity3d.com/download_unity/linux/unity-editor-installer-5.3.4f1+20160317.sh
sudo sh unity-editor-installer-5.3.4f1+20160317.sh

# run Unity
./unity-editor-5.3.4f1/Editor/Unity

# if background is pink, install:
sudo apt-get install lib32stdc++6 -y

install python modules:

pip install -r python-agent/requirements.txt

Install Unity.

install python modules:

pip install -r python-agent/requirements.txt

Building simulator on Windows10 (Japanese)

download data:

./fetch.sh

Next, run python module as a server.

cd python-agent
python server.py

Open unity-sample-environment with Unity and load Scenes/Sample.

Press Start Buttn. This will take a few minuts for loading caffe model.

You can watch reward history:

cd python-agent
python plot_reward_log.py

This graph is a "sample" scene result. It takes about 6 hours on GPU Machine.

Sample scene result movie

SampleLikesAndDislikes scene result movie

This is supported only SYNC mode. ASYNC mode is not supprted.

Start multi agent server:

cd python-agent
python multi_agent.py --agent-count=2

Next, open unity-sample-environment and load Scenes/SampleMultiAgent.

You can watch reward history:

python plot_reward_log.py --log-file=reward_0.log

• Client: Unity
• Server: python module
• Communication: Socket (WebSocket over TCP) using MessagePack

Select "SceneController" in Hierarchy tab and change "Time Scale".

This will make simulation more faster, but it will be slow gui response.

• MessagePack for Unity

• Copyright (C) 2011-2012 Kazuki Oikawa, Kazunari Kida

• Apache License, Version 2.0

• Assets/Packages/msgpack-unity

• websocket-sharp

• Copyright (c) 2010-2016 sta.blockhead

• The MIT License (MIT)

• Assets/Packages/websocket-sharp

• Apache License, Version 2.0
• Original Developer: (DWANGO ARTIFICIAL INTELLIGENCE LABORATORY)

If you created intelligent agents, please let me know about it to "[email protected]". We will make showcase varied intelligent agents.