“Successful critical thinking would include recognising that correlation is not causation” — You know this concept already don’t you? Correlation is not causation. I think that most people know this phrase, but how many times a day do you see it used to call out …
Most people are merely “interested” — in changing themselves, getting healthy, getting rich — but that’s all they are. They prefer the small dopamine boost after reading an inspirational article than actually changing. Which is hard. Sometimes very hard.
We will present a simple solution to solve the Cart-Pole problem based on random search. The idea is the following, assume your agent has a function that can be used to determine what action to perform (i.e. move the cart left or right ) based on the observation it receives from the environment. In reinforcement learning world, the function that maps observations to actions is known as the policy function. The goal of the agent learning process is to select the optimal policy which produces the maximum possible total reward.