2

In the course of a scientific work, I will discuss the different types of reinforcement learning. However, I have difficulties to find these different types.

So, into which subcategories can reinforcement learning be divided? For example, the following subdivisions seem to be useful

  • Model-free and Model-based
  • Dynamic Programming, Monte Carlo and Temporal Difference

Any others?

nbro
  • 39,006
  • 12
  • 98
  • 176
jackless
  • 23
  • 3

1 Answers1

4

Your two suggestions are not mutually exclusive. If you go by this process, you'll have to do a "Cartesian product" of a bunch of different RL categorizations which would get out of hand. I recommend, if you can, to describe some sort of "RL taxonomy" instead. By this I mean describing different RL characterizations without assuming they're mutually exclusive.

To add to your list :

  • On-policy or off-policy
  • Value based or policy gradient
harwiltz
  • 1,091
  • 1
  • 6
  • 6
  • 1
    Maybe you could include a diagram like [this one](https://spinningup.openai.com/en/latest/spinningup/rl_intro2.html). It's your choice, but sometimes diagrams help. – nbro Jul 03 '20 at 21:42
  • +1 for the diagram nbro posted, that's a great visualization for what I was trying to describe – harwiltz Jul 04 '20 at 00:07