Orbit is a open-source project and a collection of reinforcement learning environments.
In this environment the paddle needs to hit the ball.
Episode ends after each 1000 frames or when ball touchs the ground.
0
- Move paddle to left.
1
- Do nothing.
2
- Move paddle to right.
- X position of paddle.
- X and Y position of ball.
- X and Y velocity of ball.
+3
when paddle hit the ball.-3
when ball touchs the ground.-0.1
when paddle moves.