Adversarial attacks on Deep Reinforcement Learning (RL)

Deep Reinforcement Learning for Trading

AI agent game competition - Reinforcement learning (Monte Carlo Tree Search, Deep Q-learning, Minimax)

Reinforcement Learning for Autonomous Satellite Constellation Scheduling and Earth Observation Optimization

Graduation Project 2023, an intelligent traffic management system that combines reinforcement learning along with simulation.

Learn to play roulette using Reinforcemente Learning (RL) with a DQN agent

A simple game aimed at training an artificial agent to play it considerably well.

基于DQN算法的投球2D仿真，没有考虑空气阻力，仅用于算法理解

Reinforcement Learning: Q-Learning and Deep Q-Learning to train artificial agents that can play the famous game of Nim.

Implement the Scripted and DQN Agents for Pysc2 BuildMarines Minigame with PyTorch

The aim of this repository is the analysis and study of computer intelligence and in-depth learning techniques in the development of intelligent gaming agents.

Dieses Projekt implementiert eine Snake-Umgebung gemäss dem OpenAI Gym Standard und trainiert einen Reinforcement Learning Agenten (PPO) mit stable-baselines3.

FinSearch Research Competition

This project integrates MicroK8s (lightweight Kubernetes) with Reinforcement Learning (RL) for adaptive autoscaling in startups, reducing cloud costs by up to 30% compared to traditional solutions (HPA/CA).

Fine-tuning LLM agents w online RL for XiangQi (Chinese Chess)

Python code for teaching turtles how to play variations of "tag" with Deep Q-Networks.

A game-playing AI that uses Deep-Q Networks to play Checkers

DQN Atari Pong game

ELEC70121 Trustworthy Artificial Intelligence in Medical Imaging - final project

This project implements a Deep Q-Network (DQN) agent trained in a custom Gymnasium environment called HomeFoodEnvStatic. The agent learns to navigate a grid-based world to reach a desired food goal while avoiding distractions ("hell states") using reinforcement learning.