Skip to content

arplaboratory/l2f-constant-reward

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Learning to Fly Using a Constant Reward Function

Dependencies

Ubuntu

Tested in a vanilla Ubuntu 24.04 Docker container

apt update
apt install -y build-essential cmake libhdf5-dev libboost-dev libboost-system-dev libboost-serialization-dev

Please also install Intel MKL for fast training (https://www.intel.com/content/www/us/en/developer/tools/oneapi/onemkl-download.html)

apt install -y gpg-agent wget
wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list
apt update
apt install -y intel-oneapi-mkl-devel
export MKL_ROOT=/opt/intel/oneapi/mkl/latest

macOS

brew install cmake hdf5 boost

Apple Accelerate (the MKL equivalent) is installed by default on macOS and should be detected by the build system automatically

Build

mkdir build
cd build
cmake ..
cmake --build . --target training evaluation
cd ..

Run

./build/src/training --parameter-file parameters/output/crazyflie.json --num-runs 1
./build/src/evaluation

UI

cmake .. -DRL_TOOLS_ENABLE_BOOST_BEAST=ON
cmake --build . --target evaluation_ui
docker run -it --rm -p 8000:8000 rltools/ui-server:v0.1-l2f
./build/src/evaluation_ui

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published