An open API service indexing awesome lists of open source software.

https://github.com/arnabsaha7/reinforcement-learning-projects

Projects on Reinforcement Learning
https://github.com/arnabsaha7/reinforcement-learning-projects

gym gymnasium openai pyga python reinforcement-learning

Last synced: 6 months ago
JSON representation

Projects on Reinforcement Learning

Awesome Lists containing this project

README

          

## Reinforcement Learning Projects

### Super Mario Bros using Reinforcement Learning
**Description:**
This project implements a Reinforcement Learning (RL) agent to play the classic Super Mario Bros game. The agent is trained to navigate through the game's environment using deep learning techniques.

**Technologies:**
![Python](https://img.shields.io/badge/-Python-3776AB?style=flat&logo=python&logoColor=white)
![OpenAI Gym](https://img.shields.io/badge/-OpenAI%20Gym-000000?style=flat&logo=openaigym&logoColor=white)
![TensorFlow](https://img.shields.io/badge/-TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white)
![PyTorch](https://img.shields.io/badge/-PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white)
![OpenCV](https://img.shields.io/badge/-OpenCV-5C3EE8?style=flat&logo=opencv&logoColor=white)

---

### Maze Project
**Description:**
This project explores reinforcement learning algorithms applied to solving maze navigation tasks. It involves implementing algorithms such as Q-learning or Deep Q-Networks (DQN) to find optimal paths through maze environments.

**Technologies:**
![Python](https://img.shields.io/badge/-Python-3776AB?style=flat&logo=python&logoColor=white)
![OpenAI Gym](https://img.shields.io/badge/-OpenAI%20Gym-000000?style=flat&logo=openaigym&logoColor=white)
![TensorFlow](https://img.shields.io/badge/-TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white)
![PyTorch](https://img.shields.io/badge/-PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white)

---

### Cartpole
**Description:**
The Cartpole project focuses on the classic control problem where an inverted pendulum (pole) must be balanced on top of a moving cart. Reinforcement learning techniques are used to train an agent to keep the pole balanced by controlling the cart's movements.

**Technologies:**
![Python](https://img.shields.io/badge/-Python-3776AB?style=flat&logo=python&logoColor=white)
![OpenAI Gym](https://img.shields.io/badge/-OpenAI%20Gym-000000?style=flat&logo=openaigym&logoColor=white)
![TensorFlow](https://img.shields.io/badge/-TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white)
![PyTorch](https://img.shields.io/badge/-PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white)

---

### MLTrader Bot
**Description:**
This project develops an automated trading bot that utilizes machine learning for sentiment analysis to inform trading decisions. It integrates with the Alpaca API for trade execution and uses FinBERT for sentiment estimation from news headlines.

**Technologies:**
![Python](https://img.shields.io/badge/-Python-3776AB?style=flat&logo=python&logoColor=white)
![Lumibot](https://img.shields.io/badge/-Lumibot-FFFFFF?style=flat&logoColor=black)
![Alpaca API](https://img.shields.io/badge/-Alpaca%20API-000000?style=flat&logo=alpaca&logoColor=white)
![FinBERT](https://img.shields.io/badge/-FinBERT-FF5733?style=flat&logoColor=white)
![PyTorch](https://img.shields.io/badge/-PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white)
![Timedelta](https://img.shields.io/badge/-Timedelta-000000?style=flat&logoColor=white)