Making Similar Mistakes Twice

Learnings from 12 Hour Hackathon

We’re exactly like Artificial Intelligence.

Deep learning, specifically.

One of the core parts of deep learning is reinforcement learning. It’s similar to operant conditioning in psychology where we’re rewarded or punished based on a set of behaviors. In reinforcement learning, an agent is exploring a new environment and as they are taking actions, changing states they get rewarded or punished.