Option Discovery for Autonomous Generation of Symbolic Knowledge

TL;DR

This paper presents an empirical study of an autonomous agent that explores an environment, discovers options without predefined goals, and reuses this knowledge to solve tasks using symbolic planning.

Contribution

It introduces a method for autonomous option discovery and knowledge abstraction in an exploratory agent, enabling goal achievement through symbolic planning.

Findings

Discovered options can be abstracted into probabilistic symbolic models.

The agent successfully generates plans to achieve extrinsic goals.

The approach works in the Treasure Game domain.

Abstract

In this work we present an empirical study where we demonstrate the possibility of developing an artificial agent that is capable to autonomously explore an experimental scenario. During the exploration, the agent is able to discover and learn interesting options allowing to interact with the environment without any pre-assigned goal, then abstract and re-use the acquired knowledge to solve possible tasks assigned ex-post. We test the system in the so-called Treasure Game domain described in the recent literature and we empirically demonstrate that the discovered options can be abstracted in an probabilistic symbolic planning model (using the PPDDL language), which allowed the agent to generate symbolic plans to achieve extrinsic goals.