Hard to understand for a newbie in Deep RL. A formal definition of what is a skill ("A skill is simply a policy.") would help. ### Typos: - "guaranteeing that is has maximum entropy" - "We discuss the the log p(z) term in Appendix B." - "so it much first gather momentum" - "While are skills are learned"
I agree with the previous comment. The article seems to aim at people who are already familiar with reinforcement (not necessarily deep, or based on neural networks I guess) and its usual benchmark. The implementations are not detailed, the authors lay stress on the general idea (which is relatively simple to get), and its visual results which look quite spectacular.
> The article seems to aim at people who are already familiar with X and its usual benchmark. That can be said about quite every article.
>> The article seems to aim at people who are already familiar with X and its usual benchmark. > That can be said about quite every article. Sure, let me rephrase then. The article does not remind the reader of much contextual information and standard definitions of the field. Thus, that's not the appropriate paper if you want to get a general idea of the field.
This was precisely the very reason of the hypertext creation. The main idea of hypertext, the father of the contemporary web, was to help the people to navigate between documents and easily access all related definitions and previous works. Wikipedia [tells](https://en.wikipedia.org/wiki/World_Wide_Web#History) us the following: > In March 1989 Berners-Lee issued a proposal to the management at CERN for a system called "Mesh" that referenced ENQUIRE, a database and software project he had built in 1980, which used the term "web" and described a more elaborate information management system based on links embedded in readable text: _"Imagine, then, the references in this document all being associated with the network address of the thing to which they referred, so that while reading this document you could skip to them with a click of the mouse."_ But people just cannot use it properly, don't sure why. Maybe it's too difficult to add some hyperlinks to the paper, or too complex to click on them after. Perhaps the consciousness of the majority of people are naturally evolved or shaped by society in such a way that hyperlinks are not natural, and the concept "googling something" you don't know for the moment, is located nearby "blasphemy" in people's mind concept map. Another reason will be that we don't have a time or desire to do all necessary work to understand the article, so we ask authors to write very clear ans easily consuming text. But the authors also have no time to do this. However, there is a small hope, that in the near future some computers will be capable to read scientific papers, google all necessary stuff, and, using reader public profile, transform the information in the form that reader will be capable to digest easily.
The problem from my point of view is that a scientist has close to no incentive to give additional context information. For example, an author would not add a link to a Wikipedia page, as it is considered (rightly or wrongly) under the scientific quality standards. Even worse: I have observed that in most scientific communities, it is expected that you don't give too much details on the some definitions, assumptions or computations if they are considered as "common knowledge". In other words, adding too much details is understood as a sign that you are an outsider of the community. In anyway, hyperlinks would not solve everything, as the writer still has to target a given "level of knowledge" of the reader, he would make the information understandable by a specific audience. Typically, when I read about a field which is new to me, I first go to Wikipedia. The level of details of a Wikipedia page is widely heterogeneous: some pages are too basic for what I already know, but others are too elaborate, and as you said, I am not willing to spend the "focusing time" necessary for me to understand such a page if I cannot even evaluate if I will have a much better understanding of the paper afterwards. The author is certainly more capable of evaluating what are the context information which are useful to understand what he writes, but you are right that it costs time to him as well. So, I think that in a way, the problem can be seen as an economic one, of which focusing time is the main resource.
> For example, an author would not add a link to a Wikipedia page, as it is considered (rightly or wrongly) under the scientific quality standards I would not agree, some scientists already write blog-posts about their beloved subjects using a lot of hyperlinks to Wikipedia and other sites, consider for example [Igor Pak's](https://igorpak.wordpress.com/2015/05/26/the-power-of-negative-thinking-part-i-pattern-avoidance/) or [Terence Tao's](https://terrytao.wordpress.com/2009/04/26/szemeredis-regularity-lemma-via-random-partitions/) blogs. Currently, such blog-posts are considered complementary to "real" scientific publications. But but one day everything will change.

#### You comment anonymously! You will not be able to edit/delete the comment.

Use $\LaTeX$ to type formulæ and markdown to format text.