Learning from Machine Learning

Reinforcement learning, often abbreviated RL, is a way for a machine to learn by interacting with an environment, receiving rewards or penalties as feedback, and eventually learn to take actions in a way that maximizes cumulative rewards over time. Think of it the way one teaches a dog to sit by offering them treats.

Jason Wei, in his post Life lessons from reinforcement learning, talks of the ways in which teaching machines how to learn this way has taught him lessons for his own life:

But even after I graduated school, I had a habit of studying how other people found success and trying to imitate them. Sometimes it worked, but eventually I realized that I would never surpass the full ability of someone else because they were playing to their strengths which I didn’t have. … Beating the teacher requires walking your own path.

or as Bashō said:

“Do not seek to follow in the footsteps of the wise; seek what they sought.”