Fernando Corbacho

Pablo de los Riscos, Fernando Corbacho

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.

Fernando Corbacho

Adaptive behavior is mainly the result of adaptive brains. We go a step beyond and claim that the brain does not only adapt to its surrounding reality but rather, it builds itself up to constructs its own reality. That is, rather than just trying to passively understand its environment, the brain is the architect of its own reality in an active process where its internal models of the external world frame how its new interactions with the environment are assimilated. These internal models represent relevant predictive patterns of interaction all over the different brain structures: perceptual, sensorimotor, motor, etc. The emergence of adaptive behavior arises from this self-constructive nature of the brain, based on the following principles of organization: self-experimental, self- growing, and self-repairing. Self-experimental, since to ensure survival, the self-constructive brain (SCB) is an active machine capable of performing experiments of its own interactions with the environment by mental simulation. Self-growing, since it dynamically and incrementally constructs internal structures in order to build a model of the world as it gathers statistics from its interactions with the environment. Self-repairing, since to survive the SCB must also be robust and capable of finding ways to repair parts of previously working structures and hence re-construct a previous relevant pattern of activity.