Course talk:CPSC522/Action Selection for MDPs

From UBC Wiki

Contents

Thread titleRepliesLast modified
Critique 2008:38, 13 March 2018
Critique 1022:27, 12 March 2018

Critique 2

  • 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). 5
  • The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 5
  • The abstract is a concise and clear summary. 5
  • There were appropriate (original) examples that helped make the topic clear. 5
  • There was appropriate use of (pseudo-) code. 4
  • It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 5
  • 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
  • This page should be highlighted as an exemplary page for others to emulate. 4

If I was grading it out of 20, I would give it: 17

Comment:

Explicitly state which papers you are referring to as paper 1 and paper 2 early in the page (perhaps in the abstract)
I would recommend adding figures from the papers, particularly for MAXQ-OP directed acyclic graph and the performance in the evaluation.
MAXQ-OP section is very pseudo code heavy. It would be nice to have a sentence explaining each function along with the pseudo code itself.

JocelynMinns (talk)08:38, 13 March 2018

Critique 1

Comments[wikitext]

The focus of the article is clear and it is organized well. However, while those of us exposed to the subject of MDP numerous times during the course may be able to follow this page, it needs more intuitive discussion to serve as a standalone article. Much of the discussion relies on interpreting the pseudo-code and it could be improved by a follow-up higher-level description. In particular:

  1. In AOT, what this "admissible heuristic" function is doing is unclear.
  2. In UCT, the role of the "Bonus" term deserves a higher-level description, (e.g. its role in balancing explotation and exploration), since that is the core of the algorithm.
  3. In MAXQ-OP, the concept of a hierarchical decomposition is important but not much explanation is provided. Can any MDP be decomposed this way? Perhaps an example of an MDP decomposition would be helpful.

Scheme[wikitext]

  • The topic is relevant for the course. 5
  • 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). 5
  • 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. 1
  • There was appropriate use of (pseudo-) code. 5
  • It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 3
  • 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. -
  • The references and links to external pages are well chosen. -
  • 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. 3
  • If I was grading it out of 20, I would give it: 14
KumseokJung (talk)22:27, 12 March 2018