A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.
-
Updated
Nov 4, 2024 - Python
A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.
A toolkit for working with RDDL domains in Python3.
Planning through backpropagation using TensorFlow.
Tensorflow is not only an well designed deep learning toolbox, but also a standard symbolic programming framework. In this repository, we show how to use tensorflow to do classical planning task on deterministic, continous action, continous space problems.
Probabilistic planning in continuous state-action MDPs in TensorFlow.
Planning using Reinforcement Learning
Hosts domain and instance RDDL files, covering problems from a wide range of disciplines, integration with the pyRDDLGym ecosystem.
Symbolic compilation of RDDL domains, Dynamic Bayes net (DBN) visualization, symbolic dynamic programming (SDP).
JAX compilation of RDDL description files, and a differentiable planner in JAX.
RDDL syntax highlighting for Visual Studio Code
Docker files for connecting the PROST planner with pyRDDLGym.
Gurobi compilation of RDDL description files to mixed-integer programs, and optimization tools.
Graphical integrated development environment for RDDL.
A command line tool for generating an unlimited number of RDDL instance files of customisable complexity.
Wrappers for reinforcement learning algorithms (i.e. stable baselines 3, RLlib) to work with pyRDDLGym.
Add a description, image, and links to the rddl topic page so that developers can more easily learn about it.
To associate your repository with the rddl topic, visit your repo's landing page and select "manage topics."