A simple framework for experimenting with Reinforcement Learning in Python.

Online Replanning in Belief Space for Partially Observable Task and Motion Problems

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

Feature selection for maximizing expected cumulative reward

Pathfinding Using Reinforcement Learning

Probabilistic planning in continuous state-action MDPs in TensorFlow.

Using reinforcement learning and genetic algorithms to improve traffic flow and reduce vehicle waiting times in a single-lane two-way junction simulator by coordinating traffic signal schedules.

In- and post- process methods for optimizing explanations path based on newly defined quantitative explanation metrics

Principles & Applications of Artificial Intelligence at Amirkabir University of Technology course projects

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

Implemented reinforcement learning algorithms, including Value-Iteration and Q-Learning, for a 2D grid world Markov Decision Process resembling a Pac-man game. Also applied the Mini-Max algorithm and common path-planning techniques such as A*, Dijkstra, and bidirectional search.

Sample projects to learn reinforcement learning and deep reinforcement learning in practice.

MDP and Dynamic Programming Practical Lab

Mathematical implementation of robotics algorisms such as MDP, EKF, RRT, and etc.

A grid world simulation environment

Fundamental of AI course which focuses on search, multiagents, mdp and reinforcement learning algorithms.

A RDDL simulator running in TensorFlow.

DQN in Dynamic Channel Access

✨ Un générateur de mot de passe aléatoire totalement fait en Python par moi, et en français.

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