Mdp Python Packages

mdplib

Fast solvers for infinite-horizon discounted Markov Decision Processes (value iteration, Gauss-Seidel VI, policy iteration, Q-learning, SARSA) with a C++/pybind11 backend.

simple-rl

A simple framework for experimenting with Reinforcement Learning in Python.

rddlrepository

Hosts domain and instance RDDL files, covering problems from a wide range of disciplines, integration with the pyRDDLGym ecosystem.

tfrddlsim

A RDDL simulator running in TensorFlow.

blackhc-mdp

Make it easy to specify simple MDPs that are compatible with the OpenAI Gym.

tf-mdp

Probabilistic planning in continuous state-action MDPs in TensorFlow.

mdp-solver-ic

Fast solvers for infinite-horizon discounted Markov Decision Processes (value iteration, Gauss-Seidel VI, policy iteration, Q-learning, SARSA) with a C++/pybind11 backend.

upgrade-policy-optimizer

Python library aimed at solving stochastic decision problems with value iteration.

modeldriveprotocol-client

Model Drive Protocol (MDP): MDP turns runtime-local capabilities into MCP-reachable capabilities.

mdpproblog

MDP-ProbLog is a framework to represent and solve (infinite-horizon) MDPs specified by probabilistic logic programming.

rlephant

A simple tool for writing and reading episodes of reinforcement learning environments to and from disk.