Lunar-lander

A Deep Q - Learning Model for training on Lunar Lander environment provided by OpenAI Gym

Description

This is my TensorFlow implementations of Deep Q learning model proposed in Playing Atari with Deep Reinforcement Learning

The task is to land the space-ship between the flags smoothly. The ship has 3 throttles in it. One throttle points downward and other 2 points in the left and right direction. With the help of these, you have to control the Ship. There are 2 version for this task. One is discrete version which has discrete action space and other is continuous which has continuous action space.
In order to solve the episode you have to get a reward of +200 for 100 consecutive episodes. I solved both the version under 400 episodes.
This environment was in my capstone project as part of my University of Alberta Specialization which did not use Tensorflow to solve the Environment.
I have also included a trained model to quickly test out the environment.

To run the script :
```
 python lunar_lander.py
```
Make sure to change the variable values according to your needs after running the first time to see different results.
To test the model trained simply run :
```
 python test_model.py
```