Goal Agnostic Planning using Maximum Likelihood Paths in Hypergraph World Models

TL;DR

This paper introduces a hypergraph-based planning algorithm that combines machine learning and AI principles, providing optimal solutions and predictive models for autonomous agents in complex environments.

Contribution

It presents a novel goal-agnostic planning method using maximum likelihood paths in hypergraph world models, integrating probabilistic Dijkstra's algorithm with theoretical performance bounds.

Findings

Proves optimality of the planning algorithm

Provides mathematical bounds on learning performance

Demonstrates effectiveness on hierarchical planning problems

Abstract

In this paper, we present a hypergraph--based machine learning algorithm, a datastructure--driven maintenance method, and a planning algorithm based on a probabilistic application of Dijkstra's algorithm. Together, these form a goal agnostic automated planning engine for an autonomous learning agent which incorporates beneficial properties of both classical Machine Learning and traditional Artificial Intelligence. We prove that the algorithm determines optimal solutions within the problem space, mathematically bound learning performance, and supply a mathematical model analyzing system state progression through time yielding explicit predictions for learning curves, goal achievement rates, and response to abstractions and uncertainty. To validate performance, we exhibit results from applying the agent to three archetypal planning problems, including composite hierarchical domains, and highlight empirical findings which illustrate properties elucidated in the analysis.