alexandrulita91 / mountain-car-v0

A car is on a one-dimensional track, positioned between two "mountains". The goal is to drive up the mountain on the right; however, the car's engine is not strong enough to scale the mountain in a single pass. Therefore, the only way to succeed is to drive back and forth to build up momentum.

MountainCar-v0

A car is on a one-dimensional track, positioned between two "mountains". The goal is to drive up the mountain on the right; however, the car's engine is not strong enough to scale the mountain in a single pass. Therefore, the only way to succeed is to drive back and forth to build up momentum.

OpenAI Gym

OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like pong or pinball. Gym is an open source interface to reinforcement learning tasks.

Reinforcement learning algorithms

• Deep Q-learning (off-policy, model-free)

Demo video

https://www.youtube.com/watch?v=9-wYKN2I5G0

Requirements

• Python 3.6 or 3.7
• CUDA Toolkit 10.1
• cuDNN v7.6.5
• Pipenv

How to install the packages

You can install the required Python packages using the following command:

• pipenv sync

How to run it

You can run the script using the following command:

• pipenv run python mountain_car_v0_dqn.py