Vectors for Common-sense Reasoning

The physical world is filled with constraints. You can open a door, but only if it isn’t locked. You can douse a fire, but only if a fire is present. You can throw a rock or drop a rock or even, under certain circumstances, converse with a rock, but you cannot traverse it, enumerate it, or impeach it.

The term affordances refers to the subset of possible actions which are feasible in a given situation. Human beings detect these affordances automatically, often subconsciously, but it is not uncommon for autonomous learning agents to attempt impossible or even ridiculous actions, thus wasting effort on futile behaviors.

Fortunately, there is a way to harvest common-sense knowledge about these behaviors. Recent research in our laboratory shows that word embeddings can be used as a common-sense knowledge base. When this common-sense knowledge is applied to old school text-based adventure games like Zork, the agents using common sense knowledge demonstrate impressive performance improvements.

Read the full research paper.