In typical multiagent teamwork settings, the teammates are either programmed together, or are otherwise provided with standard communication languages and coordination protocols. ...
Imitation represents a powerful approach for programming and autonomous learning in robot and computer systems. An important aspect of imitation is the mapping of observations to ...
We highlight the limitations of formal methods by exhibiting two results in recursive function theory: that there is no effective means of finding a program that satisfies a given...
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without n...
With the proliferation of consumer computing devices with varied display and input characteristics, it has become desirable to develop interactive systems that are usable across m...