DQN
所属分类:人工智能/神经网络/深度学习
开发工具:C/C++
文件大小:20KB
下载次数:25
上传日期:2015-04-09 14:00:59
上 传 者:
jxqqq1
说明: 谷歌DeepMind2015年2月发表的人工智能算法,可以在雅达利2600游戏机的49个游戏中击败人类专业玩家
(human-level control through RL)
文件列表:
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\convnet.lua (2038, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\convnet_atari3.lua (354, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\initenv.lua (4777, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\LICENSE (1611, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\net_downsample_2x_full_y.lua (244, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\NeuralQLearner.lua (12634, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\nnutils.lua (1501, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\Rectifier.lua (538, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\Scale.lua (557, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\train_agent.lua (7671, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn\TransitionTable.lua (11596, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\install_dependencies.sh (3094, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\run_cpu (1576, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\run_gpu (1576, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\dqn (0, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning\roms (0, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning\Human_Level_Control_through_Deep_Reinforcement_Learning (0, 2015-02-25)
Human_Level_Control_through_Deep_Reinforcement_Learning (0, 2015-03-23)
----- DQN 3.0 -----
This project contains the source code of DQN 3.0, a Lua-based deep reinforcement
learning architecture, necessary to reproduce the experiments
described in the paper "Human-level control through deep reinforcement
learning", Nature 518, 529–533 (26 February 2015) doi:10.1038/nature14236.
To replicate the experiment results, a number of dependencies need to be
installed, namely:
* LuaJIT and Torch 7.0
* nngraph
* Xitari (fork of the Arcade Learning Environment (Bellemare et al., 2013))
* AleWrap (a lua interface to Xitari)
An install script for these dependencies is provided.
Two run scripts are provided: run_cpu and run_gpu. As the names imply,
the former trains the DQN network using regular CPUs, while the latter uses
GPUs (CUDA), which typically results in a significant speed-up.
----- Installation instructions -----
The installation requires Linux with apt-get.
Note: In order to run the GPU version of DQN, you should additionally have the
NVIDIA CUDA (version 5.5 or later) toolkit installed prior to the Torch
installation below.
This can be downloaded from https://developer.nvidia.com/cuda-toolkit
and installation instructions can be found in
http://docs.nvidia.com/cuda/cuda-getting-started-guide-for-linux
To train DQN on Atari games, the following components must be installed:
* LuaJIT and Torch 7.0
* nngraph
* Xitari
* AleWrap
To install all of the above in a subdirectory called 'torch', it should be enough to run
./install_dependencies.sh
from the base directory of the package.
Note: The above install script will install the following packages via apt-get:
build-essential, gcc, g++, cmake, curl, libreadline-dev, git-core, libjpeg-dev,
libpng-dev, ncurses-dev, imagemagick, unzip
----- Training DQN on Atari games -----
Prior to running DQN on a game, you should copy its ROM in the 'roms' subdirectory.
It should then be sufficient to run the script
./run_cpu
Or, if GPU support is enabled,
./run_gpu
Note: On a system with more than one GPU, DQN training can be launched on a
specified GPU by setting the environment variable GPU_ID, e.g. by
GPU_ID=2 ./run_gpu
If GPU_ID is not specified, the first available GPU (ID 0) will be used by default.
----- Options ------
Options to DQN are set within run_cpu (respectively, run_gpu). You may,
for example, want to change the frequency at which information is output
to stdout by setting 'prog_freq' to a different value.
近期下载者:
相关文件:
收藏者: