Welcome to my Reinforcement Learning (RL) repository! 🚀
This repository contains implementations of various RL algorithms applied to different environments, including Super Mario and Trading simulations. It serves as a learning space where I explore deep reinforcement learning, experiment with different architectures, and apply RL to real-world problems.
- 📁 SuperMario/ – Implementing RL to play Super Mario using Deep Q-Networks (DQN).
- 📁 Trading/ – Using RL for stock/crypto trading simulations.
- 📄 README.md – This document, explaining the repository's purpose and structure.
- 📄 requirements.txt – List of dependencies for setting up the environment.
🕹️ Implementing RL agents to play Super Mario Bros using OpenAI Gym, gym-super-mario-bros, and deep learning techniques.
🔹 Algorithm Used: Deep Q-Network (DQN) with experience replay
🔹 Environment: gym-super-mario-bros
🔹 Objective: Train an agent to play and complete levels efficiently
📊 Implementing Reinforcement Learning-based trading agents for stock/crypto trading simulations.
🔹 Algorithm Used: A2C (for now)
🔹 Dataset: Stock market/crypto price data - Yfinance API
🔹 Objective: Optimize buy/sell strategies to maximize returns
To set up and run the projects locally, follow these steps:
# Clone the repository
git clone https://github.com/bhanurana430/Reinforcement-Learning.git
cd Reinforcement-Learning