https://github.com/mehrab-kalantari/mountain-car-ddqn

Double deep q network implementation in OpenAI Gym's "Mountain Car" environment
https://github.com/mehrab-kalantari/mountain-car-ddqn

ddqn double-deep-q-learning double-deep-q-network double-deep-q-networks double-dqn mountain-car reinceforcement-learning

Last synced: about 2 months ago
JSON representation

Double deep q network implementation in OpenAI Gym's "Mountain Car" environment

• Host: GitHub
• URL: https://github.com/mehrab-kalantari/mountain-car-ddqn
• Owner: Mehrab-Kalantari
• Created: 2023-09-22T16:07:25.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-09-24T13:35:30.000Z (over 1 year ago)
• Last Synced: 2024-10-24T15:53:00.067Z (2 months ago)
• Topics: ddqn, double-deep-q-learning, double-deep-q-network, double-deep-q-networks, double-dqn, mountain-car, reinceforcement-learning
• Language: Python
• Homepage:
• Size: 17.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Mountain Car Double Deep Q Network

Double deep q network implementation in OpenAI Gym's "Mountain Car" environment 

## What is OpenAI Gym's "Mountain Car" environment

![l](https://www.gymlibrary.dev/_images/mountain_car.gif)

The Mountain Car MDP is a deterministic MDP that consists of a car placed stochastically at the bottom of a sinusoidal valley, with the only possible actions being the accelerations that can be applied to the car in either direction. The goal of the MDP is to strategically accelerate the car to reach the goal state on top of the right hill. 

[Complete Details](https://www.gymlibrary.dev/environments/classic_control/mountain_car/)

## Double Deep Q Network

DDQN architecture

![model](https://rubikscode.net/wp-content/uploads/2021/07/Featured-11.png)

## Network

We use the following network for this problem

![m](sample/model.png)