Abstract Policy gradient methods have become one of the most popular classes algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many these credit assignment: assessing an agent’s contribution to overall performance, which crucial learning good policies. We propose a novel algorithm called Dr.Reinforce explicitly tackles this combining differenc...

Gender differences in reward sensitivity and information processing were examined in two studies using a dynamic decision-making task. In Experiment 1, the optimal strategy involved forgoing an option that provided larger immediate rewards in favor of one yielding larger delayed rewards. In Experiment 2, the optimal strategy was to select the option that provided larger immediate rewards becaus...

Impulsivity is characterized in part by heightened sensitivity to immediate relative to future rewards. Although previous research has suggested that "high discounters" in intertemporal choice tasks tend to prefer immediate over future rewards because they devalue the latter, it remains possible that they instead overvalue immediate rewards. To investigate this question, we recorded the reward ...

Using original survey data, this paper examines whether monetary rewards and honor rewards encourage or discourage blood donation. On the use of monetary rewards, we find that i) the overall sample’s response to monetary rewards is positive, and ii) people who volunteer more frequently, people who donated blood regularlt and people who donate blood to help others respond less positively to mone...

Two studies examined whether the detrimental effects of attention to rewards on delay of gratification in waiting situations holds-or reverses-in working situations. In Study 1, preschoolers waited or worked for desired delayed rewards. Delay times increased when children worked in the presence of rewards but, as predicted, this increase was due to the distraction provided by the work itself. n...

Impulsivity is a stable personality trait associated with myopic choice behavior that favors immediate rewards over larger, delayed rewards and is often characterized as maladaptive inside and outside of the laboratory. An alternative view suggests that the consequences of trait impulsivity depend on the nature of the task environment. On this view, the optimal level of impulsivity varies acros...