Lunar Lander using policy gradients

Say our agent is driving the space vehicle and the goal of our agent is to land correctly on the landing pad. If our agent (lander) lands away from the landing pad, then it loses the reward and the episode will get terminated if the agent crashes or comes to rest. Four discrete actions available in the environment are do nothing, fire left orientation engine, fire main engine, and fire right orientation engine.

Now we will see how to train our agents to correctly land on the landing pad with policy gradients. Credit for the code used in this section goes to Gabriel (

First, we import the necessary libraries:

import tensorflow as tfimport numpy ...

Get Hands-On Reinforcement Learning with Python now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.