All Projects → VowpalWabbit → Reinforcement_learning

VowpalWabbit / Reinforcement_learning

Licence: mit
Predict/log/learn/update reinforcement learning loop

Programming Languages

cpp
1120 projects

Projects that are alternatives of or similar to Reinforcement learning

Neural Architecture Search With Rl
Minimal Tensorflow implementation of the paper "Neural Architecture Search With Reinforcement Learning" presented at ICLR 2017
Stars: ✭ 37 (-21.28%)
Mutual labels:  reinforcement-learning
Machine Learning From Scratch
Succinct Machine Learning algorithm implementations from scratch in Python, solving real-world problems (Notebooks and Book). Examples of Logistic Regression, Linear Regression, Decision Trees, K-means clustering, Sentiment Analysis, Recommender Systems, Neural Networks and Reinforcement Learning.
Stars: ✭ 42 (-10.64%)
Mutual labels:  reinforcement-learning
Deterministic Gail Pytorch
PyTorch implementation of Deterministic Generative Adversarial Imitation Learning (GAIL) for Off Policy learning
Stars: ✭ 44 (-6.38%)
Mutual labels:  reinforcement-learning
Fullstackmachinelearning
Mostly free resources for end-to-end machine learning engineering, including open courses from CalTech, Columbia, Berkeley, MIT, and Stanford (in alphabetical order).
Stars: ✭ 39 (-17.02%)
Mutual labels:  reinforcement-learning
Qualia2.0
Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.
Stars: ✭ 41 (-12.77%)
Mutual labels:  reinforcement-learning
Bullet3
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Stars: ✭ 8,714 (+18440.43%)
Mutual labels:  reinforcement-learning
Fragile
Framework for building algorithms based on FractalAI
Stars: ✭ 36 (-23.4%)
Mutual labels:  reinforcement-learning
Ml In Tf
Get started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Stars: ✭ 45 (-4.26%)
Mutual labels:  reinforcement-learning
Awesome Mlss
List of summer schools in machine learning + related fields across the globe
Stars: ✭ 1,001 (+2029.79%)
Mutual labels:  reinforcement-learning
Orbit
Open source collection of Reinforcement Learning Environments.
Stars: ✭ 44 (-6.38%)
Mutual labels:  reinforcement-learning
Deepbootcamp
Solved lab problems, slides and notes of the Deep Reinforcement Learning bootcamp 2017 held at UCBerkeley
Stars: ✭ 39 (-17.02%)
Mutual labels:  reinforcement-learning
Blocks
Blocks World -- Simulator, Code, and Models (Misra et al. EMNLP 2017)
Stars: ✭ 39 (-17.02%)
Mutual labels:  reinforcement-learning
Tf2.0 reinforcement learning
Basic reinforcement learning implementation with tensorflow version 2.0
Stars: ✭ 43 (-8.51%)
Mutual labels:  reinforcement-learning
Deepqlearning.jl
Implementation of the Deep Q-learning algorithm to solve MDPs
Stars: ✭ 38 (-19.15%)
Mutual labels:  reinforcement-learning
Async Deeprl
Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning
Stars: ✭ 44 (-6.38%)
Mutual labels:  reinforcement-learning
Awesome Deep Rl
For deep RL and the future of AI.
Stars: ✭ 985 (+1995.74%)
Mutual labels:  reinforcement-learning
Deep Q Learning
Minimal Deep Q Learning (DQN & DDQN) implementations in Keras
Stars: ✭ 1,013 (+2055.32%)
Mutual labels:  reinforcement-learning
Deep traffic
MIT DeepTraffic top 2% solution (75.01 mph) 🚗.
Stars: ✭ 47 (+0%)
Mutual labels:  reinforcement-learning
Biped trajectory optimization
Implementing trajectory optimization on bipedal system
Stars: ✭ 45 (-4.26%)
Mutual labels:  reinforcement-learning
Gym Gridworlds
Gridworld environments for OpenAI gym.
Stars: ✭ 43 (-8.51%)
Mutual labels:  reinforcement-learning

Linux Build Status) MacOS Build Status Windows Build status

reinforcement_learning

git submodule update --init --recursive

Ubuntu

Dependencies

sudo apt-get install libboost-all-dev libssl-dev

Install Cpprest

cd ~
git clone https://github.com/Microsoft/cpprestsdk.git cpprestsdk
cd cpprestsdk
# Checkout 2.10.1 version of cpprestsdk
git checkout e8dda215426172cd348e4d6d455141f40768bf47
git submodule update --init
cd Release
mkdir build
cd build
cmake ..
make -j `nproc`
make install
cd ../../../
rm -rf cpprestsdk

Install Flatbuffers

cd ~
git clone https://github.com/google/flatbuffers.git flatbuffers
cd ./flatbuffers
# 1.10.0 release commit
git checkout 925c1d77fcc72636924c3c13428a34180c30f96f
mkdir build
cd build
cmake .. -DFLATBUFFERS_BUILD_TESTS=Off -DFLATBUFFERS_INSTALL=On -DCMAKE_BUILD_TYPE=Release -DFLATBUFFERS_BUILD_FLATHASH=Off
make -j `nproc`
sudo make install
cd ../../
rm -rf flatbuffers

Build

mkdir build
cd build
cmake ..
make

Troubleshooting

If you get an error similar to the following on MacOS when running cmake .., then you may be able to fix it by supplying the OpenSSL path to CMake.

Make Error at /usr/local/Cellar/cmake/3.14.4/share/cmake/Modules/FindPackageHandleStandardArgs.cmake:137 (message):
  Could NOT find OpenSSL, try to set the path to OpenSSL root folder in the
  system variable OPENSSL_ROOT_DIR (missing: OPENSSL_INCLUDE_DIR)
Call Stack (most recent call first):
  /usr/local/Cellar/cmake/3.14.4/share/cmake/Modules/FindPackageHandleStandardArgs.cmake:378 (_FPHSA_FAILURE_MESSAGE)
  /usr/local/Cellar/cmake/3.14.4/share/cmake/Modules/FindOpenSSL.cmake:413 (find_package_handle_standard_args)
  /usr/local/Cellar/cmake/3.14.4/share/cmake/Modules/CMakeFindDependencyMacro.cmake:48 (find_package)
  /usr/local/lib/cpprestsdk/cpprestsdk-config.cmake:11 (find_dependency)
  CMakeLists.txt:9 (find_package)

This can be fixed by invoking CMake similar to the following:

cmake -DOPENSSL_ROOT_DIR=`brew --prefix openssl` -DOPENSSL_LIBRARIES=`brew --prefix openssl`/lib ..

Installing cpprestsdk on Ubuntu18.04 using apt-get may result in cmake failing with:

CMake Error at CMakeLists.txt:9 (find_package):
  By not providing "Findcpprestsdk.cmake" in CMAKE_MODULE_PATH this project
  has asked CMake to find a package configuration file provided by
  "cpprestsdk", but CMake did not find one.

  Could not find a package configuration file provided by "cpprestsdk" with
  any of the following names:

    cpprestsdkConfig.cmake
    cpprestsdk-config.cmake

  Add the installation prefix of "cpprestsdk" to CMAKE_PREFIX_PATH or set
  "cpprestsdk_DIR" to a directory containing one of the above files.  If
  "cpprestsdk" provides a separate development package or SDK, be sure it has
  been installed.

The workaround is to specify where to search

cmake .. -DCMAKE_PREFIX_PATH=/usr/lib/x86_64-linux-gnu/cmake

Test

mkdir build
cd build
cmake ..
make rltest
make test

Windows

Windows dependencies are managed through Vcpkg and Nuget.

vcpkg install cpprestsdk:x64-windows
vcpkg install flatbuffers:x64-windows

You'll need to add the flatbuffers tool directory to your PATH aswell: <vcpkg_root>\installed\x64-windows\tools\flatbuffers

MacOS

MacOS dependencies can be managed through homebrew.

brew install cpprestsdk flatbuffers openssl

In order to build using homebrew dependencies, you must invoke cmake this way:

mkdir build
cd build
cmake -DOPENSSL_ROOT_DIR=`brew --prefix openssl` -DOPENSSL_LIBRARIES=`brew --prefix openssl`/lib ..

Build + Test

Set VcpkgIntegration environment variable to vcpkg.targets file on your machine

Example: VcpkgIntegration=c:\s\vcpkg\scripts\buildsystems\msbuild\vcpkg.targets

Ensure that the v140 toolset is installed in Visual Studio 2017.

Open rl.sln in Visual Studio 2017. Build Release or Debug x64 configuration.

Experimental - CMake on Windows (Do not mix with checked in solution)

Using CMake is an alternate way to configure and build the project. Currently it only supports the C++ projects. All dependencies are managed through Vcpkg:

# Warning only use if generating solution with CMake)
vcpkg install cpprestsdk:x64-windows
vcpkg install zlib:x64-windows
vcpkg install boost-system:x64-windows
vcpkg install boost-program-options:x64-windows
vcpkg install boost-test:x64-windows
vcpkg install boost-uuid:x64-windows

Run the following to generate a solution file to open in Visual Studio 2017:

mkdir build
cd build
cmake .. -G "Visual Studio 15 2017 Win64" -DCMAKE_TOOLCHAIN_FILE=[vcpkg root]\scripts\buildsystems\vcpkg.cmake -DVCPKG_TARGET_TRIPLET=x64-windows
.\reinforcement_learning.sln

Make targets

  • doc - Python and C++ docs
  • _rl_client - Python bindings
  • rlclientlib - rlclient library
  • rltest - unit tests
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].