Self-control failure is a ubiquitous and troubling problem people face. This article reviews psychological models of self-control and describes a new integrative approach based on construal level theory (e.g., Trope & Liberman, 2003). This construal-level perspective proposes that people’s subjective mental construals or representations of events impacts self-control. Specifically, more abstrac...

Standard multi-armed bandits model decision problems in which the consequences of each action choice are unknown and independent of each other. But in a wide variety of decision problems – from drug dosage to dynamic pricing – the consequences (rewards) of different actions are correlated, so that selecting one action provides information about the consequences (rewards) of other actions as wel...

Scaling multiagent reinforcement learning to domains with many agents is a complex problem. In particular, multiagent credit assignment becomes a key issue as the system size increases. Some multiagent systems suffer from a global reward signal that is very noisy or difficult to analyze. This makes deriving a learnable local reward signal very difficult. Difference rewards (a particular instanc...

I worked in an organization that had just finished a high-profile project. We been challenged to develop chipset for new customer on accelerated schedule. hadn’t quite met all the milestones or specifications, but we were close. Overall, successful. Most importantly, was pleased. led one of product development teams. At start project, our general manager provided additional motivation. He sugge...

Offshore employees (expatriates) working abroad are an important part of any organisational workforce, working and competing globally. The specific requirements of expatriates are quite different as compared to the local workforce of that particular company. These requirements range from base salary to the educational needs of their families, children, and spouses. The employers especially work...

We introduce reinforcement learning for heterogeneous teams in which rewards an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents the domain. Motivating domains include coordination of varied robotic platforms, incur different costs same action, but share overall goal. present two templates this setting with rewards: a g...