AbstractThe locus coeruleus (LC) in the pons is the major source of noradrenaline (NA) in the brain. Two modes of LC firing have been associated with distinct cognitive states: changes in tonic rates of firing are correlated with global levels of arousal and behavioural flexibility, whilst phasic LC responses are evoked by salient stimuli. Here, we unify these two modes of firing by modelling the response of the LC as a correlate of a prediction error when inferring states for action planning under Active Inference (AI).We simulate a classic Go/No-go reward learning task and a three-arm foraging task and show that, if LC activity is considered to reflect the magnitude of high level ‘state-action’ prediction errors, then both tonic and phasic modes of firing are emergent features of belief updating. We also demonstrate that when contingencies change, AI agents can update their internal models more quickly by feeding back this state-action prediction error – reflected in LC firing and noradrenaline release – to optimise learning rate, enabling large adjustments over short timescales. We propose that such prediction errors are mediated by cortico-LC connections, whilst ascending input from LC to cortex modulates belief updating in anterior cingulate cortex (ACC).In short, we characterise the LC/ NA system within a general theory of brain function. In doing so, we show that contrasting, behaviour-dependent firing patterns are an emergent property of the LC’s crucial role in translating prediction errors into an optimal mediation between plasticity and stability.Author SummaryThe brain uses sensory information to build internal models and make predictions about the world. When errors of prediction occur, models must be updated to ensure desired outcomes are still achieved. Neuromodulator chemicals provide a possible pathway for triggering such changes in brain state. One such neuromodulator, noradrenaline, originates predominantly from a cluster of neurons in the brainstem – the locus coeruleus (LC) – and plays a key role in behaviour, for instance, in determining the balance between exploiting or exploring the environment.Here we use Active Inference (AI), a mathematical model of perception and action, to formally describe LC function. We propose that LC activity is triggered by errors in prediction and that the subsequent release of noradrenaline alters the rate of learning about the environment. Biologically, this describes an LC-cortex feedback loop promoting behavioural flexibility in times of uncertainty. We model LC output as a simulated animal performs two tasks known to elicit archetypal responses. We find that experimentally observed ‘phasic’ and ‘tonic’ patterns of LC activity emerge naturally, and that modulation of learning rates improves task performance. This provides a simple, unified computational account of noradrenergic computational function within a general model of behaviour.