Reward prediction error (RPE) is crucial for learning and memory, yet their distinct influences on episodic memory remain underexplored. Previous studies have shown two models for the influence of RPE on memory-signed RPE (SRPE) or unsigned RPE (URPE) effects. In the current study, thirty participants completed a prediction-feedback assessment integrated with a study-recognition task. Electroencephalogram (EEG) was recorded throughout the experiment. Our results showed that recognition accuracy improved when rewards deviated from expectations, irrespective of the direction (positive or negative) of the deviation. EEG analyses revealed that during the recognition phase, the late positive component was predominantly associated with URPE effects. In the earlier time windows of reward feedback, FRN and P300 components reflected SRPE effects. In contrast, robust URPE effects emerged in the later time windows, as evidenced by both univariate and multivariate analyses. Importantly, the URPE effects of representational similarity were correlated with that of subsequent recognition performance. These findings demonstrate that RPE is differentially processed across memory encoding stages, with URPE exerting a dominant influence. Our results highlight the critical role of unexpected feedback in memory formation and provide novel insights into the mechanisms underlying RPE in episodic memory.
Keywords: RPE; URPE; episodic memory; neural representation.
Copyright © 2025. Published by Elsevier Inc.
