Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
This addresses the challenge of building adaptable AGI agents and robots for dynamic environments, though it appears incremental as it extends existing causal learning methods to specific robotic scenarios.
The paper tackles the problem of enabling autonomous robots to adapt to unexpected environmental changes by constructing new causal models, demonstrating that active causal structure learning with latent variables can learn complex detour behaviors when encountering a transparent barrier, achieving optimal planning in previously unpredictable situations.
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.