People are emotional, and machines are not. That constrains their communication, and defines a key challenge for the information sciences. Different groups have addressed it from d...
As multiagent environments become more prevalent we need to understand how this changes the agent-based paradigm. One aspect that is heavily affected by the presence of multiple a...
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
We show that the class of monotone 2O( √ log n)-term DNF formulae can be PAC learned in polynomial time under the uniform distribution from random examples only. This is an expo...
The training experiences needed by a learning system may be selected by either an external agent or the system itself. We show that knowledge of the current state of the learner...