While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
Satinder P. Singh, Andrew G. Barto, Roderic A. Gru...
The general goal of the paper is to show the normative/deontic nature of conventions. Conventions are traditionally defined as regularity of behavior based on expectations evolved...
This paper addresses the problem of automated advice provision in settings that involve repeated interactions between people and computer agents. This problem arises in many real ...
When we communicate with others in a most primitive way like face-to-face conversation, we normally gather at a common physical place. This physical constraint has been recognized ...
Social agents have recently been more frequently used in the user interface. However, so far not many studies have been conducted on what impact such interfaces have on users beha...