https://github.com/lhvy/taxi-v3-q-learning
A simple Q-learning implementation in OpenAI Gym's "Taxi-v3" environment.
https://github.com/lhvy/taxi-v3-q-learning
gym machine-learning openai-gym python-3 python3 q-learning reinforcement-learning
Last synced: 4 months ago
JSON representation
A simple Q-learning implementation in OpenAI Gym's "Taxi-v3" environment.
- Host: GitHub
- URL: https://github.com/lhvy/taxi-v3-q-learning
- Owner: lhvy
- License: mit
- Created: 2020-08-15T06:26:38.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2022-11-11T13:09:38.000Z (almost 3 years ago)
- Last Synced: 2025-05-12T19:46:21.404Z (5 months ago)
- Topics: gym, machine-learning, openai-gym, python-3, python3, q-learning, reinforcement-learning
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 6
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Taxi-v3 Q-Learning
A simple Q-learning implementation in OpenAI Gym's "Taxi-v3" environment.
## What is OpenAI Gym?
[OpenAI Gym](https://gym.openai.com/) is a toolkit for developing and comparing reinforcement algorithms. It provides a wide range of environments with different reinforcement learning tasks.
It can be found on GitHub [here](https://github.com/openai/gym) and documentation is [here.](https://gym.openai.com/docs)
## Setup & Running the code.
Python 3 is required and can be downloaded [here.](https://www.python.org/downloads/)
### Installing required libraries.
```
pip3 install -r requirements.txt
```
### Running the agent.
```
py agent.py
```
## Possible Improvements
- Command line arguments to modify the amount of training episodes.
- Saving and loading the q-table.
- Tuning alpha, gamma and epsilon by decaying over training episodes.