Social stress reactivity alters reward and punishment learning

Abstract

To examine how stress affects cognitive functioning, individual differences in trait vulnerability (punishment sensitivity) and state reactivity (negative affect) to social evaluative threat were examined during concurrent reinforcement learning. Lower trait-level punishment sensitivity predicted better reward learning and poorer punishment learning; the opposite pattern was found in more punishment sensitive individuals. Increasing state-level negative affect was directly related to punishment learning accuracy in highly punishment sensitive individuals, but these measures were inversely related in less sensitive individuals. Combined electrophysiological measurement, performance accuracy and computational estimations of learning parameters suggest that trait and state vulnerability to stress alter cortico-striatal functioning during reinforcement learning, possibly mediated via medio-frontal cortical systems.

Fig. 1

Probabilistic learning task. During training, each pair is presented separately. Participants have to select one of the two stimuli, slowly integrating ‘Correct’ and ‘Incorrect’ feedback (each stimulus has a unique probabilistic chance of being ‘Correct’) in order to maximize their accuracy. During the testing phase, each stimulus is paired with all other stimuli and participants must choose the best one, without the aid of feedback. Note that the letter and percentage are not presented to the participant, nor are the green boxes surrounding the choice. During the training phase, participants must choose which stimulus they feel is correct, without the aid of feedback. Measures of reward and punishment learning are taken from the test phase, hypothesized to reflect the operations of a slow, probabilistic integrative system during training.

Fig. 2

Depiction of the social evaluative threat stress manipulation during the second performance of the task (T2).

Fig. 3

Performance and learning rate changes due to stress reactivity. (A) Under stress, the Low BIS group was characterized by the tendency for more accurate reward learning and less accurate punishment learning; this pattern trended towards the opposite direction High BIS group. These same patterns are reflected more strongly in test phase learning rate changes, where lower learning rates are hypothesized to reflect more effective slow probabilistic integration. (B) The degree of negative affect during stress also differentially altered punishment learning: relating to poorer punishment learning in the Low BIS group yet better punishment learning in the High BIS group.

Fig. 4

Time-frequency representations of EEG power at the FCz electrode. EEG plots are shown for response- and feedback-locked events during training (T1 and T2).

Fig. 5

Increasing negative affect was related to a general pattern of greater internalization of punishment during training, as reflected by an increase in response-locked theta power and a concurrent decrease in negative feedback-locked theta power.

Fig. 6

Response and negative-feedback locked theta in relation to performance (values for interaction plots are median splits ±SE). In the Low BIS group (left column), theta power to feedback alone predicted subsequent high conflict NoGo learning (asterisk indicates main effect p < .05). In the High BIS group (right column), an inverted-U type interaction between response- and feedback-locked theta predicted subsequent accuracy in high conflict NoGo learning, where high total theta activities or low total theta activities predicted better learning (asterisk indicates interaction effect p < .05).