Learning How to Solve Bubble Ball

TL;DR

This paper introduces a hierarchical predictive framework that effectively solves complex physics-based puzzles like Bubble Ball by iteratively updating models based on failed attempts, demonstrating success on various levels.

Contribution

The paper presents a novel hierarchical approach combining geometric, kinematic, and dynamic models to solve physics-based puzzles with limited data.

Findings

Successfully solves many Bubble Ball levels

Uses iterative model updates from failed attempts

Applicable to other physics-based games

Abstract

"Bubble Ball" is a game built on a 2D physics engine, where a finite set of objects can modify the motion of a bubble-like ball. The objective is to choose the set and the initial configuration of the objects, in order to get the ball to reach a target flag. The presence of obstacles, friction, contact forces and combinatorial object choices make the game hard to solve. In this paper, we propose a hierarchical predictive framework which solves Bubble Ball. Geometric, kinematic and dynamic models are used at different levels of the hierarchy. At each level of the game, data collected during failed iterations are used to update models at all hierarchical level and converge to a feasible solution to the game. The proposed approach successfully solves a large set of Bubble Ball levels within reasonable number of trials. This proposed framework can also be used to solve other physics-based games, especially with limited training data from human demonstrations.