ICACT20220065 Question.1
Questioner: 201120072@fzu.edu.cn 2022-02-12 오전 12:19:51 |
ICACT20220065 Answer.1
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-12 오전 12:19:51
Chrome  Click!! |
| As mentioned earlier, the state includes day, time, decision, weather information. Action was defined as an item that user could select. Why is a equal to s_t in lines 4 and 8 of algorithm 2 in the paper? Please explain the relationship between a and s_t. |
|
ICACT20220065 Question.2
Questioner: 201120072@fzu.edu.cn 2022-02-12 오전 12:21:50 |
ICACT20220065 Answer.2
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-12 오전 12:21:50
Chrome Click!! |
| On page 9 of the PPT, according to the description of algorithm 2, different r values will be obtained every hour, and the Q-value will be updated accordingly. When updating the Q table, whether the Q-value obtained in 24 hours will be accumulated. |
|
ICACT20220065 Question.3
Questioner: 201120072@fzu.edu.cn 2022-02-12 오전 12:22:24 |
ICACT20220065 Answer.3
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-12 오전 12:22:24
Chrome Click!! |
| On page 14 of the PPT, in order to obtain the maximum value of learned policy, whether to obtain the optimal strategy for each hour separately, or to arrange and combine the actions that can be selected for each hour of the day and select the strategy that can achieve the maximum value. In other words, when setting the state, whether to set each hour as a state or treat a whole day as a state. |
|
ICACT20220065 Question.4
Questioner: tomayoon@ieee.org 2022-02-14 오전 3:47:30 |
ICACT20220065 Answer.4
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-14 오전 3:47:30
Chrome Click!! |
| First of all, thank you for the good research paper and presentation contents. I would like to know more about the research environment used in this study, and also in detail about the equipment & operating systems, development languages and software libraries you used. |
|
ICACT20220065 Question.5
Questioner: 201120072@fzu.edu.cn 2022-02-14 오후 12:49:15 |
ICACT20220065 Answer.5
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-14 오후 12:49:15
Chrome Click!! |
| Can you provide youtube link? |
|
ICACT20220065 Question.6
Questioner: isb6655@korea.ac.kr 2022-02-15 오후 2:20:50 |
ICACT20220065 Answer.6
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-15 오후 2:20:50
Chrome Click!! |
| Thank you for your presentation. I would like to know about simulation where rewards are accumulated. |
|
ICACT20220065 Question.7
Questioner: jianms@nfu.edu.tw 2022-02-16 오전 1:29:30 |
ICACT20220065 Answer.7
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-16 오전 1:29:30
Chrome Click!! |
| According to the presentation ,I would like to know , you mention that at slide 10.
to train an episode spends a day, is it in a real-time?
how many days to train a model. |
|
ICACT20220065 Question.8
Questioner: honhonzone@gmail.com 2022-02-16 오후 1:23:36 |
ICACT20220065 Answer.8
Answer by Auhor yh0360@chungbuk.ac.kr 2022-02-16 오후 1:23:36
Chrome Click!! |
| User preference is a good topic in many research. I would like to know if user preference can use to predict personal stance/ideology. |
|
