Reinforcement Learning Quotes

Early in my doctoral training at Cornell University, I became immersed in the behavioral decision theory paradigm.

The way positive reinforcement is carried out is more important than the amount.

You have to teach your algorithm what it can do and what it cannot do because, otherwise, there is a risk that the algorithms will learn the tricks of the old cartels.

The strange flavour of AI work is that people try to put together long sets of rules in strict formalisms which tell inflexible machines how to be flexible.

Artificial Intelligence (AI) is the science of how to get machines to do the things they do in the movies.

Properly used, positive reinforcement is extremely powerful.

Learning would be exceedingly laborious, not to mention hazardous, if people had to rely solely on the effects of their own actions to inform them what to do.

Deep learning is a subfield of machine learning, which is a vibrant research area in artificial intelligence, or AI.

The deep learning techniques, while relatively easy to learn, are quite foreign to traditional engineering modalities. It takes a different mindset and a relaxation of the presumption of control. The practitioners are like magi, sequestered from the rest of a typical engineering process.

With the Google Brain project, we made the decision to build deep learning processes on top of Google's existing infrastructure.

You could claim that moving from pixelated perception, where the robot looks at sensor data, to understanding and predicting the environment is a Holy Grail of artificial intelligence.

We behavioralists differ from our more traditional brethren in the way we characterize agents in the economy.

We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.

How teach again, however, what has been taught correctly and incorrectly learned a thousand thousand times, throughout the millenniums of mankind's prudent folly? That is the hero's ultimate difficult task.

Humans are unbelievably data efficient. You don't have to drive 1 million miles to drive a car, but the way we teach a self-driving car is have it drive a million miles.