Deep Reinforcement Learning for mobile robot navigation, a robot learns to navigate to a random goal point from random moves to adopting a strategy, in a simulated maze environment while avoiding dynamic obstacles.

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

Tic-Tac-Toe Q-Learning is a beginner-friendly example of using reinforcement learning.

In this Assignment, you will teach RL Agents to pickup packages on a grid-world. The environment you will be using is called the Four-Rooms domain

MuJoCo-based reinforcement learning with Q-learning-driven curriculum for robust humanoid locomotion under perturbations.

This project proposes a simulation-based reinforcement learning framework for safe medicine dosage optimization. A virtual patient environment is mathematically modeled to simulate infection progression, toxicity accumulation, and immunity dynamics.

"Multi-Environment RL Benchmark: Optimizing Q-Learning via Reward Shaping & Hyperparameter Tuning" / "다중 환경 강화학습 벤치마크: 보상 설계(Reward Shaping) 및 하이퍼파라미터 튜닝을 통한 Q-Learning 최적화"

A command-line turn‑based arena where you face an AI that learns with Q‑Learning: the agent buckets battle states into a Q‑table, updates action values after each fight using rewards and an epsilon‑greedy policy. It is ideal for experimenting with reinforcement learning, tweaking strategies and teaching core RL concepts through hands‑on pl

A 1vs1 game using reinforcement learning

This is an introductory tutorial to tabular Q-learning in Norwegian.

An implementation of iterative prisoner dilemma with reinforcement learning via q_table (NOT DQN) in Python with around 30 strategies

Implementation of core reinforcement learning algorithms with PyTorch

A simple Q-Table implementation for Rust

Solving Flappy Bird with RL.

Q learning algorithm example in python

Tabular Q-learning agent for tic-tac-toe. Trained against a uniformly-random opponent; no minimax, no hard-coded rules.

We use python software and NumPy library to implement the Q-learning method , train an Agent to solve a Reinforcement Learning Problem

This is a machine learning project developed at woodhack 2018 - demonstrating that machine learning can be done from scratch, even without a framework.

Implementations of Reinforcement Learning algorithms

42 project that involves implementing Reinforcement Learning