Autonomous agents for realtime multiplayer ice-hockey
Published:
Abhishek Divekar, Jason Housman, Ankita Sinha, Alex Stoken
Description: We design an automated agent to play 2-on-2 games in SuperTuxKart IceHockey. Our two-stage system composes of a "vision" stage which takes as input the image of the player's Field of View and predicts world-state attributes. For vision, we train a multi-task CenterNet model (with U-Net backend), to predict whether hockey puck was on-screen (classification), puck's x-y coordinates (aimpoint regression) and distance from player (regression). These are consumed by a "controller" stage which return actions that update the world-state by "dribbling" puck towards goal, or defending against the opposing AI team.
My contribution: Generated training dataset of 40k images, coded and trained multi-task CenterNet model for vision stage of pipeline, wrote sections of report.
Resources: [Technical report]