© 2020 by </-\> AyranOlckers.

AWS DeepRacer Reward Function

AWS and Udacity are teaming up to teach machine learning and prepare students to test their skills by participating in the world’s first autonomous racing league—the AWS DeepRacer League. Students with the top lap times will earn full scholarships to the Machine Learning Engineer Nanodegree program.

The program begins August 1 and will run through October 31, 2019. You can join the scholarship community at any point during these 3 months and immediately enroll in Udacity’s specialized AWS DeepRacer course.

Once you enroll, you’ll work through the brief AWS DeepRacer course consisting of several short modules that will prepare you to create, train, and fine-tune a reinforcement learning model in the AWS DeepRacer 3D racing simulator. Throughout the program–including while you progress through the course and while you work on your racing submissions–you’ll have access to a custom scholarship student community where you can get pro tips from experts and exchange ideas with your classmates. 

Each month you’ll be able to pit your skills against others in virtual races in the AWS DeepRacer console. Students will compete for top spots in each month’s unique race course. Students that record the top lap times in August, September, and October 2019 will qualify for one of 200 full scholarships to the Machine Learning Engineer Nanodegree program. 

In @params object:

{

"all_wheels_on_track": Boolean,       # flag to indicate if the vehicle is on the track

"x": float,                                            # vehicle's x-coordinate in meters

"y": float,                                            # vehicle's y-coordinate in meters

"distance_from_center": float,           # distance in meters from the track center

"is_left_of_center": Boolean,             # Flag to indicate if the vehicle is on the left side to the track center or not.

"heading": float,                                # vehicle's yaw in degrees

"progress": float,                               # percentage of track completed

"steps": int,                                       # number steps completed

"speed": float,                                   # vehicle's speed in meters per second (m/s)

"streering_angle": float,                    # vehicle's steering angle in degrees

"track_width": float,                           # width of the track

"waypoints": [[float, float], … ],         # list of [x,y] as milestones along the track center

"closest_waypoints": [int, int]            # indices of the two nearest waypoints.

}

Language: Python
Purpose: Part of the AWS + Udacity Scholarship Challenge
Motivation: To Learn Reinforcement Learning through Udacity and AWS