Learning Purposeful Behaviour in the Absence of Rewards

TL;DR

This paper introduces an algorithm that enables agents to learn purposeful and exploratory behaviors in environments lacking reward signals by identifying intrinsic goals and constructing temporally extended actions.

Contribution

The paper presents a novel method for learning purposeful behavior without rewards by identifying purposes as intrinsic goals and building options to facilitate exploration.

Findings

Enables purposeful exploration without reward signals

Constructs temporally extended actions (options) based on intrinsic purposes

Improves exploration in sparse reward environments

Abstract

Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a notion of progress. However, some domains have no such reward signal, or have a reward signal so sparse as to appear absent. Without reward feedback, agent behaviour is typically random, often dithering aimlessly and lacking intentionality. In this paper we present an algorithm capable of learning purposeful behaviour in the absence of rewards. The algorithm proceeds by constructing temporally extended actions (options), through the identification of purposes that are "just out of reach" of the agent's current behaviour. These purposes establish intrinsic goals for the agent to learn, ultimately resulting in a suite of behaviours that encourage the agent to visit different parts of the state space. Moreover, the approach is particularly suited for settings where rewards are very sparse, and such behaviours can help in the exploration of the environment until reward is observed.