GithubHelp home page GithubHelp logo

samkatt / fba-pomdp Goto Github PK

View Code? Open in Web Editor NEW
19.0 2.0 9.0 19.81 MB

Factored model-based Bayesian Reinforcement Learning framework

License: GNU General Public License v3.0

CMake 0.43% Shell 0.02% Python 1.85% C++ 96.13% ReScript 1.56%

fba-pomdp's Introduction

(Factored) Bayes-Adaptive POMDP

A code base to run (Bayes-Adaptive) reinforcement learning experiments on partially observable domains. This project is meant for reinforcement learning researchers to compare different methods. It contains various different environments to test the methods on, of which all partially observable and discrete. Note that this project has mostly been written for personal use, research, and thus may lack the documentation that one would typically expect from open source projects.

Related research:

Installation

mkdir wherever/you/want && cd wherever/you/want
cmake -DCMAKE_BUILD_TYPE=Release /path/to/root/of/this/project
make

Requirements:

Usage

To run planning algorithms (no learning)

./planning -D episodic-tiger -v 2 -f results.txt
cat results.txt
./planning --help

To run learning approaches

Tabular BA-POMDP:

./bapomdp --help

Or Factored BA-POMDP:

./fbapomdp --help

Plotting and Processing results

See analysis/README.md

Documentation

After installation to generate the documentation in the 'doc' folder, run

cd to/the/build/directory
make docs

Development

Using IDEs

Cmake provides some support for creating project files for various IDEs. Cf. cmake --help

E.g., cmake -G should be able to do:

  Unix Makefiles                  = Generates standard UNIX makefiles.
  Ninja                           = Generates build.ninja files.
  Watcom WMake                    = Generates Watcom WMake makefiles.
  CodeBlocks - Ninja              = Generates CodeBlocks project files.
  CodeBlocks - Unix Makefiles     = Generates CodeBlocks project files.
  CodeLite - Ninja                = Generates CodeLite project files.
  CodeLite - Unix Makefiles       = Generates CodeLite project files.
  Sublime Text 2 - Ninja          = Generates Sublime Text 2 project files.
  Sublime Text 2 - Unix Makefiles = Generates Sublime Text 2 project files.
  Kate - Ninja                    = Generates Kate project files.
  Kate - Unix Makefiles           = Generates Kate project files.
  Eclipse CDT4 - Ninja            = Generates Eclipse CDT 4.0 project files.
  Eclipse CDT4 - Unix Makefiles   = Generates Eclipse CDT 4.0 project files.

Debugging & Profiling

CMake uses different build types (CMAKE_BUILD_TYPE, "Typical values include Debug, Release, RelWithDebInfo and MinSizeRel, but custom build types can also be defined."), for which you can set different flags.

For instance you can do:

cmake -DCMAKE_CXX_FLAGS_DEBUG="-O0 -ggdb -p" -DCMAKE_BUILD_TYPE=Debug /path/to/root/of/this/project
make VERBOSE=1

Alternatively, you can put these commands directly in CMakeLists.txt. E.g.:

set(CMAKE_CXX_FLAGS_DEBUG "put your flags")
set(CMAKE_CXX_FLAGS_MINSIZEREL "put your flags")
set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "put your flags")
set(CMAKE_CXX_FLAGS_RELEASE "put your flags")
set(CMAKE_C_FLAGS_DEBUG "put your flags")
set(CMAKE_C_FLAGS_MINSIZEREL "put your flags")
set(CMAKE_C_FLAGS_RELWITHDEBINFO "put your flags")
set(CMAKE_C_FLAGS_RELEASE "put your flags")

maintenance

  • formatting
    • make clang-format
  • static analysis
    • scan-build make
    • make ccpcheck
    • python run-clang-tidy.py -checks=clang-analyzer-*,cppcoreguidlines-*,misc-*,modernize-*,performance-*,readability-*,-readability-named-parameter -header-filter=src/
  • dynamic analysis (and running tests)
    • valgrind ./tests (do not forget to first compile with -DCMAKE_BUILD_TYPE=Debug)

fba-pomdp's People

Contributors

samkatt avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.