Due to its occurrence in engineering domains and implications for natural learning, the problem of utilizing unlabeled data is attracting increasing attention in machine learning....
We present a trainable sequential-inference technique for processes with large state and observation spaces and relational structure. Our method assumes "reliable observation...
The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
We present a time-lapse collection and reconstruction technique that allows following embryonic heart development at any computationally halted heart contraction state. The centra...