A C++ framework for MDPs and POMDPs with Python bindings

Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..

MDPs and POMDPs in Julia - An interface for defining, solving, and simulating fully and partially observable Markov decision processes on discrete and continuous spaces.

POMDPs in Python.

Implementation of the Deep Q-learning algorithm to solve MDPs

A gallery of POMDPs.jl problems

Online solver based on Monte Carlo tree search for POMDPs with continuous state, action, and observation spaces.

The PO-UCT (aka POMCP) algorithm implemented in Julia

Concise and friendly interfaces for defining MDP and POMDP models for use with POMDPs.jl solvers

Julia Implementation of the POMCP algorithm for solving POMDPs

Code for "Learning Belief Representations for Imitation Learning in POMDPs" (UAI 2019)

Thompson Sampling based Monte Carlo Tree Search for MDPs and POMDPs

The goal of the project is to make a robot plan its path from a source to the destination and reach the destination only by evidence and its previous transition.

hdrqn

Adaptive stress testing of black-box systems within POMDPs.jl

POMDP-based decision-making technique for Social Robots using ROS, Python and Julia

Python POMDPX parser and controller

Research on the effectiveness and improvement of Reinforcement Learning algorithms in partially observable environments.