Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots

TL;DR

This paper introduces ACSLWL, a method enabling autonomous agents and robots to actively learn and adapt internal causal models with latent variables, improving their ability to handle unexpected environmental changes and obstacles.

Contribution

It presents a novel approach for active causal structure learning with latent variables, demonstrating how robots can learn to detour around unexpected barriers by constructing new causal models.

Findings

Robots successfully learned to detour around barriers using ACSLWL.

The method improved the robot's ability to adapt to unforeseen obstacles.

Causal models enhanced the robot's planning and decision-making in dynamic environments.

Abstract

Artificial General Intelligence (AGI) Agents and Robots must be able to cope with everchanging environments and tasks. They must be able to actively construct new internal causal models of their interactions with the environment when new structural changes take place in the environment. Thus, we claim that active causal structure learning with latent variables (ACSLWL) is a necessary component to build AGI agents and robots. This paper describes how a complex planning and expectation-based detour behavior can be learned by ACSLWL when, unexpectedly, and for the first time, the simulated robot encounters a sort of transparent barrier in its pathway towards its target. ACSWL consists of acting in the environment, discovering new causal relations, constructing new causal models, exploiting the causal models to maximize its expected utility, detecting possible latent variables when unexpected observations occur, and constructing new structures-internal causal models and optimal estimation of the associated parameters, to be able to cope efficiently with the new encountered situations. That is, the agent must be able to construct new causal internal models that transform a previously unexpected and inefficient (sub-optimal) situation, into a predictable situation with an optimal operating plan.