RoboLeague

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

Installation:

Please refer to Unity ML Agents repository. Current version of RoboLeague uses ML-Agents Release 11

Completed features (identical to Rocket League):

• Ball physics
• Car aerial control and physics
• Acceleration and braking
• Single jump
• Sticky forces

Videos:

Planned features:

• Unity ML agents integration
• OpenAI gym interface integration. Unity ML already provides a wrapper
• Car ball interaction
• Dodges and second jump
• Stabilizing moment near the ground
• lateral friction model as in the game (ratio between Vx/Vy)

Useful reading (in random order):

• Unity ML-Agents Toolkit Documentation
• Physics and math of Rocket League
• Useful game values
• RLBot framework