Disentangling Reafferent Effects by Doing Nothing

An agent's ability to distinguish between sensory effects that are self-caused, and those not, is instrumental in the achievement of its goals. This thought be central a variety functions biological organisms, from perceptual stabilisation accurate motor control, higher level cognitive such as planning, mirroring sense agency. Although many these well studied AI, this important distinction rarely made explicit focus tends on associational relationship action effect or success. Toward development more general agents, we develop framework enables agents disentangle self-caused externally-caused effects. Informed by relevant models experiments robotics, sciences, demonstrate applicability through an extensive experimental evaluation over three different environments.