PyTorch implementations of algorithms from "Reinforcement Learning: An Introduction by Sutton and Barto", along with various RL research papers.

TraderNet-CRv2 - Combining Deep Reinforcement Learning with Technical Analysis and Trend Monitoring on Cryptocurrency Markets

End-to-end RL trading framework with PPO agent, self-attention neural network, custom Gym environment, and advanced backtesting.

💡 Grasp - Pick-and-place with a robotic hand 👨🏻‍💻

A Complete Collection of Deep RL Famous Algorithms implemented in Gymnasium most Popular environments

🚦 Next-generation AI Traffic Management System with real-time computer vision, reinforcement learning optimization, emergency vehicle detection, and immersive 3D visualization

Comparative research platform for Deep Reinforcement Learning and heuristic controllers in autonomous racing. Benchmarks DRL (PPO) agents against deterministic baselines in Unity MiniKart, with full reproducibility, human-like evaluation, and performance logs.

LibreGrabbe 16-DOF Robot Hand

A high-performance RL decision system for Slay the Spire. Features: Headless multi-process training, Protobuf-based cross-language communication (Java/Python/C++), and ONNX deployment.基于多进程无头环境与 Protobuf 协议的《杀戮尖塔》强化学习决策系统。集成 PPO 算法、Java Mod 数据拦截、Qt/C++ 推理客户端及云边端协同架构。

This project demonstrates how reinforcement learning can be used to analyze market behavior and learn automated stock trading strategies. It integrates technical analysis, data visualization, and RL algorithms to produce an intelligent trading simulation.

This repository is dedicated to implementing algorithms "From Scratch". It goes beyond simple API calls, diving deep into the underlying logic of everything from basic training to cutting-edge techniques like DeepSeek-R1.

This is a project for PPO S&P 500 trading

This repository implements a Proximal Policy Optimization (PPO) agent that learns to play Super Mario Bros using TensorFlow/Keras and OpenAI Gym. Features CNNs for vision, Actor-Critic architecture, and parallel environments. Train your own Mario master or run a pre-trained one!

An RL based model using PPO algorithm leveraging OpenAI Gym environment to play the popular Super Mario game.

Reinforcement learning–based controller for balancing an inverted pendulum using Proximal Policy Optimization (PPO). Supports configurable mass, length, and gravity settings (Earth, lunar, microgravity) with automated training logs, reward visualization, and performance analysis.

A legged locomotion project

Stable Baselines3

AI agents for Trackmania using the TMRL package. Implemented DDPG, PPO, and used two SAC algorithms (with one or two critics) to train cars to navigate custom-built tracks.

2D orbital rocket sim with PPO in PyTorch. Models thrust, drag, gravity, fuel; agent learns efficient ascent. Includes telemetry & visualization