Towards neoRL networks; the emergence of purposive graphs

TL;DR

This paper introduces neoRL networks that emulate cognitive maps and autonomous desires, enabling purposive behavior and real-time navigation in Euclidean spaces, inspired by early psychological theories.

Contribution

It presents a novel framework for purposive AI using neoRL modules as nodes in a network with autonomous desires, expanding the capabilities of reinforcement learning models.

Findings

NeoRL networks can navigate Euclidean spaces in real-time.

Autonomous desire modules enhance purposive behavior.

Experiments verify four principles for purposive networks.

Abstract

The neoRL framework for purposive AI implements latent learning by emulated cognitive maps, with general value functions (GVF) expressing operant desires toward separate states. The agent's expectancy of reward, expressed as learned projections in the considered space, allows the neoRL agent to extract purposive behavior from the learned map according to the reward hypothesis. We explore this allegory further, considering neoRL modules as nodes in a network with desire as input and state-action Q-value as output; we see that action sets with Euclidean significance imply an interpretation of state-action vectors as Euclidean projections of desire. Autonomous desire from neoRL nodes within the agent allows for deeper neoRL behavioral graphs. Experiments confirm the effect of neoRL networks governed by autonomous desire, verifying the four principles for purposive networks. A neoRL agent governed by purposive networks can navigate Euclidean spaces in real-time while learning, exemplifying how modern AI still can profit from inspiration from early psychology.