I've been looking online for a while for a source that explains these computations but I can't find anywhere what does the $|A(s)|$ mean. I guess $A$ is the action set but I'm not sure about that notation:

$$\frac{\varepsilon}{|\mathcal{A}(s)|} \sum_{a} Q^{\pi}(s, a)+(1-\varepsilon) \max _{a} Q^{\pi}(s, a)$$

Here is the source of the formula.

I also want to clarify that I understand the idea behind the $\epsilon$-greedy approach and the motivation behind the on-policy methods. I just had a problem understanding this notation (and also some other minor things). The author there omitted some stuff, so I feel like there was a continuity jump, which is why I didn't get the notation, etc. I'd be more than glad if I can be pointed towards a better source where this is detailed.

  • 2
    $\begingroup$ Where did you take that formula from? And what is it supposed to represent? The action selection mechanism? Normally, epsilon-greedy simply means that you choose with epsilon probability a random action instead of taking the greedily (i.e. best possible) selected action. $\endgroup$ – Daniel B. Jul 14 at 20:19
  • $\begingroup$ Sorry for that. Here's the source of the formula: incompleteideas.net/book/first/ebook/node54.html. It also shows up in the practical implementation of the epsilon-greedy algorithm (bottom of the page) $\endgroup$ – Metrician Jul 14 at 20:28
  • 2
    $\begingroup$ From the pseudo code, it is pretty clear that $A(s)$ refers to the set of all possible actions, since in step c) the algorithm iterates through all actions ($a$) (taken from that set). That it is about the actions becomes apparent from the use of $a$. $\endgroup$ – Daniel B. Jul 14 at 20:34
  • $\begingroup$ Yes I realized that I was talking more about the notation $|A(s)|$ but I get it now. Thanks. $\endgroup$ – Metrician Jul 14 at 20:44

This expression: $|\mathcal{A}(s)|$ means

  • $|\quad|$ the size of

  • $\mathcal{A}(s)$ the set of actions in state $s$

or more simply the number of actions allowed in the state.

This makes sense in the given formula because $\frac{\epsilon}{|\mathcal{A}(s)|}$ is then the probability of taking each exploratory action in an $\epsilon$-greedy policy. The overall expression is the expected return when following that policy, summing expected results from the exploratory and greedy action.

| improve this answer | |
  • $\begingroup$ Thanks for the answer ! I suspected that but I was reading deeper into it. Can you recommend anything that delves deeper into what motivates structuring that formula as: ϵ/ |A(s)| and 1 - ϵ + ϵ/ |A(s)| ? $\endgroup$ – Metrician Jul 14 at 20:41
  • 1
    $\begingroup$ @Metrician I added explanation for the formula. I expect it is being broken apart to help with an expansion or substitution. $\endgroup$ – Neil Slater Jul 14 at 20:53
  • $\begingroup$ But shouldn't be simply $1 - \frac{\epsilon}{|\mathcal{A}(s)|}$ ( instead of $1 - \epsilon + \frac{\epsilon}{|\mathcal{A}(s)|}$ ) so that it sums to 1 (by definition of a probability) when added to its complement $\frac{\epsilon}{|\mathcal{A}(s)|}$ ? $\endgroup$ – Metrician Jul 14 at 21:01
  • 1
    $\begingroup$ @Metrician: It does add up to 1, because the first term includes all $a$ values, including the maximising one. So the value from the maximising action is split across both parts. $\endgroup$ – Neil Slater Jul 14 at 21:09
  • 1
    $\begingroup$ The book you are reading has the proofs - it seems like you are partway through one them in fact. It should refer the earlier results that is using - the id (5.2) in the text is reference to where it was proven in the same book. The rest of the lines are typically just re-arrangements of terms. If you have jumped straight in to that page on some search, I suggest you read the whole book, it's a very good introduction to RL $\endgroup$ – Neil Slater Jul 14 at 21:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.