https://github.com/shallowmanica/taxi_game_rl_project
The Taxi Game from OpenAI Gym
https://github.com/shallowmanica/taxi_game_rl_project
deep-q-learning monte-carlo q-learning-algorithm reinforcement-learning tensorflow
Last synced: 5 months ago
JSON representation
The Taxi Game from OpenAI Gym
- Host: GitHub
- URL: https://github.com/shallowmanica/taxi_game_rl_project
- Owner: shallowManica
- Created: 2022-12-07T21:43:12.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2025-03-28T22:49:23.000Z (8 months ago)
- Last Synced: 2025-03-28T23:28:59.951Z (8 months ago)
- Topics: deep-q-learning, monte-carlo, q-learning-algorithm, reinforcement-learning, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 84 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Taxi Game Reinforcement Learning Project
## Overview
The Taxi Game Reinforcement Learning Project is a comprehensive implementation of various reinforcement learning algorithms to solve the Taxi-v3 environment from OpenAI's Gym. This project includes implementations of Q-learning, Monte Carlo, and Deep Q-Network (DQN) algorithms, showcasing their application in a classic control task.
## Features
- Implementation of **Q-learning**: A tabular method for reinforcement learning.
- Implementation of **Monte Carlo**: A method based on averaging sample returns.
- Implementation of **Deep Q-Network (DQN)**: A neural network-based approach to reinforcement learning.
- Visualization of training progress and results.
## Installation
To get started with the Taxi Game Reinforcement Learning project, follow these steps:
1. Clone the repository:
```bash
git clone https://github.com/shallowManica/Taxi_Game_RL_Project.git
cd Taxi_Game_RL_Project
```
## Dependencies
Here are the dependencies required for this project:
```text
gym
numpy
tensorflow
pyvirtualdisplay
ipykernel
matplotlib
pandas
keras
```
## Usage
To run the notebook and observe the results of different reinforcement learning algorithms, use the following steps:
1. Start Jupyter Notebook:
```bash
jupyter notebook
```
2. Open the `taxiGame.ipynb` notebook file and run the cells to see the implementation and results of Q-learning, Monte Carlo, and DQN algorithms on the Taxi-v3 environment.
## Directory Structure
```plaintext
Taxi_Game_RL_Project/
├── taxiGame.ipynb # Jupyter Notebook with RL implementations
├── README.md # Project documentation
```