Empathic experiences shape social behaviors and display considerable individual variation. Recent advances in computational behavioral modeling can help rigorously quantify individual differences, but remain understudied in the context of empathy and antisocial behavior. We adapted a go/no-go reinforcement learning task across social and non-social contexts such that monetary gains and losses explicitly impacted the subject, a study partner, or no one. Empathy was operationalized as sensitivity to others’ rewards, sensitivity to others’ losses, and as the Pavlovian influence of empathic outcomes on approach and avoidance behavior. Results showed that 61 subjects learned for a partner in a way that was computationally similar to how they learned for themselves. Results supported the psychometric value of individualized model parameters such as sensitivity to others’ loss, which was inversely associated with antisociality. Modeled empathic sensitivity also mapped onto motivation ratings, but was not associated with self-reported trait empathy. This work is the first to apply a social reinforcement learning task that spans affect and action requirement (go/no-go) to measure multiple facets of empathic sensitivity.