Course talk:CPSC522/Deep Q Network

It seems like the page is incomplete towards the end. This makes it a bit difficult to exactly follow what the paper is saying fully. Nevertheless, the page does cover the main aspect of the paper, namely prioritized stochastic experience replay. The notation was actually relatively easy to follow, although clarification towards the end can be useful such as what exactly is "a=0" and how TD-error is exactly measured. That said, I have not evaluated the related RL pages and perhaps this information is already covered there. Overall, it was a good read although I did find myself double-reading some parts near the end to understand them fully which may hint at the need for further clarification.

My feedback-round evaluation of the page is as follows: The topic is relevant for the course. 5 The writing is clear and the English is good. 4 The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 4.5 (defining some additional terms may be useful) The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4 The abstract is a concise and clear summary. 4 There were appropriate (original) examples that helped make the topic clear. 2 (some visuals could potentially help) There was appropriate use of (pseudo-) code. 3 (although not fully needed, it could help to see the replay algorithm) It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 3 (page doesn't seem to be complete) It is correct. 5 It was neither too short nor too long for the topic. 4 It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 5 It links to appropriate other pages in the wiki. 5 The references and links to external pages are well chosen. 5 I would recommend this page to someone who wanted to find out about the topic. 4 (5, once page is complete) This page should be highlighted as an exemplary page for others to emulate. 3 If I was grading it out of 20, I would give it: 15

Is the page missing a part? If parts are missing, I will be happy to rewrite the critique once the page is finished :)

It is not really clear which paper(s) are analized. It might be helpful to add the “sentence summary” and the “conclusions / future applications” sections, following the wiki page template. Links in “Realted pages” not working. It would be useful to add links for “Builds on”, in order to understand the theory behind the page and the papers; this would help the page to be at a more appropriate level for CPSC 522 students. The technical part is difficult to follow for someone outside the field, without appropriate links or references where non experts can find some background.

On a scale of 1 to 5, where 1 means "strongly disagree" and 5 means "strongly agree": • The topic is relevant for the course: 4 • The writing is clear and the English is good: 5 • The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds): 2 • The formalism (definitions, mathematics) was well chosen to make the page easier to understand: 3 • The abstract is a concise and clear summary: 5 • There were appropriate (original) examples that helped make the topic clear: 2 • There was appropriate use of (pseudo-) code: 5 • It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic): 4 • It is correct: 5 • It was too short for the topic (i.e., 1 means too long, 3 means about right): 2 / 3 • It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page): 5 • It links to appropriate other pages in the wiki: 2 • The references and links to external pages are well chosen: 4 • I would recommend this page to someone who wanted to find out about the topic: 3 • This page should be highlighted as an exemplary page for others to emulate: 2 If I was grading it out of 20, I would give it: 12.