PyGame-Learning-Environment

PyGame-Learning-Environment copied to clipboard

Add the Chrome T-Rex rush game to PLE. It should be a fun game for learning & playing. :smile:

Here's a random agent playing the game:

Game Spec

Observation Space

• width: 600
• height: 150
• depth: 3
• pixels in uint8

Action Space

• NO_OP
• JUMP (space key)
• DUCK (down key)
• STAND (up key)

The reason we add a STAND action is that somehow gym-ple doesn't propogate NO_OP to our game which makes our dino not able to stand up again after ducked once.

Rewards

0 for ticking, 1 for passing each obstacle and -5 for game over. We use predefined rewards from base game.

We also limit a high score to 50 (could be configured with max_score). A fun fact is that when I first try to train my agent, there's an episode lasts about 2 hours (passed 3K obstacles).

Simplification

We removed cloud and high score board in this implementation to make the observation cleaner for agents. Maybe we should add an option for this?

Credit

The implementation depends largely on @shivamshekhar 's Chrome-T-Rex-Rush.

Hi @ntasfi , I'm trying to add a new game to PLE. Hope you like it. :heart: