Reinforcement learning implies learning though. But of course that’s a term more appropriate in the context of “optimizing agents” than in the context of “optimizing prediction models”.
Reinforcement learning is a machine learning approach, there is no serious debate about that. The question is whether it is restricted to neural networks, or not.
For a bit of history on machine learning I recommend Rodney Brooks' seminal series of articles on machine learning, beginnign here:
The first article in the series, linked above has one section titled "Machine Learning Started with Games". In that section he goes over Arthur Samuel's checkers-playing program that beat a human champion in 1961.
The section also contains Brooks' description of Donald Michie's MENACE, which is widely considered to be one of the first reinforcement learning algorithms. For lack of a computer, it was implemented on a set of match boxes:
In 1960 Surgical Science did not have much pull in getting access to a digital computer. So Donald Michie himself built a machine that could learn to play the game of tic-tac-toe (Noughts and Crosses in British English) from 304 matchboxes, small rectangular boxes which were the containers for matches, and which had an outer cover and a sliding inner box to hold the matches. He put a label on one end of each of these sliding boxes, and carefully filled them with precise numbers of colored beads. With the help of a human operator, mindlessly following some simple rules, he had a machine that could not only play tic-tac-toe but could learn to get better at it.
> Reinforcement learning is a machine learning approach, there is no serious debate about that. The question is whether it is restricted to neural networks, or not.
The answer to the latter question is obviously “no”. Did anyone argue otherwise? mdp2021 suggested that redytedy may have meant that but what he or she actually wrote is “You can USE ML for RL, but the field itself is considered separate from ML and under AI in general.”
Maybe I'm confused, but I'm replying to feral's OP, where they say "Hmm, I don't see that." in response to mdp2021's comment that "Reinforcement Learning is not restricted to Neural Networks."
mdp2021: “The poster probably meant: Reinforcement Learning is not restricted to Neural Networks.”
feral: “Hmm, I don't see that.” [that RLinrtNN is probably what redytedy meant]
“In the spirit of the cutting edge, any chance you could give me a chain-of-reasoning on that inference?” [the inference that redytedy probably meant RLinrtNN]
For a bit of history on machine learning I recommend Rodney Brooks' seminal series of articles on machine learning, beginnign here:
https://rodneybrooks.com/forai-machine-learning-explained/
The first article in the series, linked above has one section titled "Machine Learning Started with Games". In that section he goes over Arthur Samuel's checkers-playing program that beat a human champion in 1961.
The section also contains Brooks' description of Donald Michie's MENACE, which is widely considered to be one of the first reinforcement learning algorithms. For lack of a computer, it was implemented on a set of match boxes:
In 1960 Surgical Science did not have much pull in getting access to a digital computer. So Donald Michie himself built a machine that could learn to play the game of tic-tac-toe (Noughts and Crosses in British English) from 304 matchboxes, small rectangular boxes which were the containers for matches, and which had an outer cover and a sliding inner box to hold the matches. He put a label on one end of each of these sliding boxes, and carefully filled them with precise numbers of colored beads. With the help of a human operator, mindlessly following some simple rules, he had a machine that could not only play tic-tac-toe but could learn to get better at it.
https://rodneybrooks.com/forai-machine-learning-explained/