Car Racing#
This environment is part of the Box2D environments. Please read that page first for general information.
Action Space |
Box([-1. 0. 0.], 1.0, (3,), float32) |
Observation Shape |
(96, 96, 3) |
Observation High |
255 |
Observation Low |
0 |
Import |
|
Description#
The easiest continuous control task to learn from pixels - a top-down racing environment. Discrete control is reasonable in this environment as well; on/off discretization is fine.
The game is solved when the agent consistently gets 900+ points. The generated track is random every episode.
Some indicators are shown at the bottom of the window along with the state RGB buffer. From left to right: true speed, four ABS sensors, steering wheel position, and gyroscope. To play yourself (it’s rather fast for humans), type:
python gym/envs/box2d/car_racing.py
Remember: it’s a powerful rear-wheel drive car - don’t press the accelerator and turn at the same time.
Action Space#
There are 3 actions: steering (-1 is full left, +1 is full right), gas, and breaking.
Observation Space#
State consists of 96x96 pixels.
Rewards#
The reward is -0.1 every frame and +1000/N for every track tile visited, where N is the total number of tiles visited in the track. For example, if you have finished in 732 frames, your reward is 1000 - 0.1*732 = 926.8 points.
Starting State#
The car starts at rest in the center of the road.
Episode Termination#
The episode finishes when all of the tiles are visited. The car can also go outside of the playfield - that is, far off the track, in which case it will receive -100 reward and die.
Arguments#
There are no arguments supported in constructing the environment.
Version History#
v0: Current version
References#
Chris Campbell (2014), http://www.iforce2d.net/b2dtut/top-down-car.
Credits#
Created by Oleg Klimov