Q-learning: Revision history

Filter revisionsshowhide

To date:

Tag filter:

Invert selection

External tools:

For any version listed below, click on its date to view it. For more help, see Help:Page history and Help:Edit summary. (cur) = difference from current version, (prev) = difference from preceding version, m = minor edit, → = section edit, ← = automatic edit summary

curprev 06:2306:23, 6 April 2024‎ Maxeto0910 talk contribs‎ m 29,274 bytes −1‎ →‎Algorithm: no sentence undo Tag: Visual edit

curprev 23:0423:04, 3 April 2024‎ Headbomb talk contribs‎ 29,275 bytes +19‎ →‎Others: | Add: journal, title. | Use this tool. Report bugs. | #UCB_Gadget undo

curprev 10:5610:56, 4 January 2024‎ OAbot talk contribs‎ m 29,256 bytes +48‎ Open access bot: hdl updated in citation with #oabot. undo

curprev 04:1904:19, 25 December 2023‎ OAbot talk contribs‎ m 29,208 bytes +16‎ Open access bot: doi updated in citation with #oabot. undo

curprev 01:3401:34, 15 December 2023‎ WikiCleanerBot talk contribs‎ m 29,192 bytes −2‎ v2.05b - Bot T20 CW#61 - Fix errors for CW project (Reference before punctuation) undo Tag: WPCleaner

curprev 03:4103:41, 6 December 2023‎ Philipnelson99 talk contribs‎ m 29,194 bytes −972‎ Reverted edits by 76.78.246.203 (talk) (HG) (3.4.11) undo Tags: Huggle Rollback
curprev 03:4003:40, 6 December 2023‎ 76.78.246.203 talk‎ 30,166 bytes +972‎ ads added undo Tag: Reverted

curprev 13:3413:34, 5 December 2023‎ C8uyPqgR talk contribs‎ 29,194 bytes +61‎ Changed from the notation used in the first edition of Richard Sutton's 'Reinforcement Learning' to that of the second edition undo

curprev 05:5205:52, 1 December 2023‎ Tsesea talk contribs‎ 29,133 bytes +21‎ →‎Deep Q-learning undo
curprev 05:5005:50, 1 December 2023‎ Tsesea talk contribs‎ 29,112 bytes +1‎ →‎Reinforcement learning undo
curprev 05:5005:50, 1 December 2023‎ Tsesea talk contribs‎ 29,111 bytes +375‎ No edit summary undo

curprev 02:3402:34, 29 November 2023‎ 2601:8c0:801:9e10:7086:3adf:df3f:5ef5 talk‎ 28,736 bytes 0‎ No edit summary undo

curprev 18:0418:04, 27 October 2023‎ Ohms law talk contribs‎ m 28,736 bytes +22‎ wlink stochastic transitions undo

curprev 14:5214:52, 22 October 2023‎ 109.49.139.84 talk‎ 28,714 bytes +31‎ Undoing my own commit - I confused the sections. undo Tag: Undo
curprev 14:5014:50, 22 October 2023‎ 109.49.139.84 talk‎ 28,683 bytes −31‎ →‎Learning rate: Replaced wrong interpretation of (learning_rate = 1) undo Tag: Reverted
curprev 14:4014:40, 22 October 2023‎ 109.49.139.84 talk‎ 28,714 bytes +34‎ →‎Algorithm: Narrowed explanation for correctness undo

curprev 14:5114:51, 24 August 2023‎ Ira Leviton talk contribs‎ 28,680 bytes +14‎ Fixed a reference. Please see Category:CS1 errors: unsupported parameter. undo

curprev 03:3603:36, 25 July 2023‎ Citation bot talk contribs‎ 28,666 bytes +10‎ Alter: title, template type. Add: chapter-url, chapter. Removed or converted URL. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Headbomb | Linked from Wikipedia:WikiProject_Academic_Journals/Journals_cited_by_Wikipedia/Sandbox2 | #UCB_webform_linked 1505/2384 undo

curprev 20:3520:35, 29 May 2023‎ Citation bot talk contribs‎ 28,656 bytes −183‎ Alter: template type. Add: isbn, class, eprint. Removed proxy/dead URL that duplicated identifier. Removed access-date with no URL. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Headbomb | Linked from Wikipedia:WikiProject_Academic_Journals/Journals_cited_by_Wikipedia/Sandbox | #UCB_webform_linked 32/41 undo

curprev 15:4215:42, 10 May 2023‎ 89.207.171.57 talk‎ 28,839 bytes +2‎ typo undo Tag: Visual edit

curprev 13:0713:07, 21 April 2023‎ Infinitepro talk contribs‎ 28,837 bytes −96‎ Fixed erroneous term in the formula. undo Tag: Visual edit

curprev 19:4319:43, 20 April 2023‎ 2003:e4:3723:823f:ac9b:5c93:28b1:3225 talk‎ 28,933 bytes +1‎ Fixed typo undo Tags: canned edit summary Mobile edit Mobile app edit iOS app edit
curprev 13:5313:53, 20 April 2023‎ 2a00:ea8:810b:3::5471 talk‎ 28,932 bytes +54‎ fixed q_new formula undo

curprev 07:5407:54, 19 April 2023‎ WikiCleanerBot talk contribs‎ m 28,878 bytes 0‎ v2.05b - Bot T20 CW#61 - Fix errors for CW project (Reference before punctuation) undo Tag: WPCleaner

curprev 15:2515:25, 11 April 2023‎ 金色黎明 talk contribs‎ 28,878 bytes +461‎ →‎Quantization: Add reference undo
curprev 15:0615:06, 11 April 2023‎ 金色黎明 talk contribs‎ 28,417 bytes +258‎ →‎Algorithm: add reference undo
curprev 14:5714:57, 11 April 2023‎ 金色黎明 talk contribs‎ 28,159 bytes +261‎ →‎Double Q-learning: Add reference undo

curprev 15:2815:28, 4 April 2023‎ GoingBatty talk contribs‎ 27,898 bytes −58‎ →‎Multi-agent learning: fixed references undo
curprev 15:2615:26, 4 April 2023‎ GoingBatty talk contribs‎ 27,956 bytes +11‎ →‎Deep Q-learning: fixed reference undo
curprev 13:2313:23, 4 April 2023‎ 金色黎明 talk contribs‎ 27,945 bytes +998‎ →‎Multi-agent learning: fix bare link undo

curprev 06:2206:22, 28 March 2023‎ WikiCleanerBot talk contribs‎ m 26,947 bytes −1‎ v2.05b - Bot T20 CW#61 - Fix errors for CW project (Reference before punctuation) undo Tag: WPCleaner

curprev 14:1714:17, 22 March 2023‎ Fschwarzentruber talk contribs‎ 26,948 bytes 0‎ →‎Double Q-learning undo Tag: Visual edit
curprev 11:4611:46, 22 March 2023‎ Fschwarzentruber talk contribs‎ 26,948 bytes +479‎ →‎Variants: add MARL variants (but I cannot insert references properly; they should be wikified sorry for that) undo Tag: Visual edit

curprev 15:0215:02, 20 February 2023‎ Citation bot talk contribs‎ 26,469 bytes −68‎ Removed proxy/dead URL that duplicated identifier. Removed access-date with no URL. | Use this bot. Report bugs. | Suggested by AManWithNoPlan | #UCB_CommandLine undo

curprev 21:4621:46, 26 January 2023‎ 2a02:8070:d85:2fa0:9c61:ec80:41e0:e2bb talk‎ 26,537 bytes −12‎ →‎Algorithm: Corrected the equation for Q_new in accordance with the description (which is correct), the error in the previous equation is obvious and a typo. undo Tags: Manual revert Mobile edit Mobile web edit
curprev 18:4018:40, 26 January 2023‎ 2a02:8108:2c0:9c:e2:3a3f:22b8:e33b talk‎ 26,549 bytes +12‎ Edited the update step so that the right fraction of the current value is added to the target. undo Tags: Reverted Visual edit

curprev 20:4020:40, 18 November 2022‎ 98.96.73.163 talk‎ 26,537 bytes +42‎ →‎Algorithm undo

curprev 02:1202:12, 8 November 2022‎ Citation bot talk contribs‎ 26,495 bytes +30‎ Add: bibcode. | Use this bot. Report bugs. | Suggested by Headbomb | #UCB_toolbar undo
curprev 02:1002:10, 8 November 2022‎ Headbomb talk contribs‎ 26,465 bytes −57‎ ce undo

curprev 20:5120:51, 22 October 2022‎ Citation bot talk contribs‎ 26,522 bytes +148‎ Alter: template type. Add: doi-access, pmc, pmid, doi, page, issue, volume, year, journal. Removed parameters. | Use this bot. Report bugs. | Suggested by AManWithNoPlan | #UCB_CommandLine undo

curprev 19:1719:17, 8 October 2022‎ 79.182.52.61 talk‎ 26,374 bytes +6‎ →‎Deep Q-learning undo
curprev 18:4818:48, 8 October 2022‎ 79.182.52.61 talk‎ 26,368 bytes −7‎ →‎Deep Q-learning undo
curprev 18:3318:33, 8 October 2022‎ 79.182.52.61 talk‎ 26,375 bytes +383‎ →‎Deep Q-learning undo

curprev 13:5113:51, 30 September 2022‎ 201.182.32.63 talk‎ 25,992 bytes +12‎ →‎Algorithm: Updated the description of the summation to better describe a misleading factor. undo

curprev 17:2917:29, 14 August 2022‎ Jackvial89 talk contribs‎ m 25,980 bytes −115‎ →‎Algorithm undo

curprev 13:0613:06, 16 July 2022‎ GuguboWIKI talk contribs‎ 26,095 bytes +13‎ →‎Reinforcement learning undo Tag: Visual edit

curprev 22:2122:21, 26 June 2022‎ Citation bot talk contribs‎ 26,082 bytes +57‎ Add: s2cid, doi, volume. | Use this bot. Report bugs. | Suggested by AManWithNoPlan | #UCB_CommandLine undo

curprev 15:2515:25, 26 May 2022‎ Citation bot talk contribs‎ 26,025 bytes +40‎ Add: s2cid, isbn. | Use this bot. Report bugs. | Suggested by Abductive | #UCB_webform 788/1030 undo

curprev 22:4722:47, 25 May 2022‎ SdkbBot talk contribs‎ m 25,985 bytes −1‎ →‎Function approximation: Removed erroneous space and general fixes (task 1) undo Tag: AWB
curprev 05:3505:35, 25 May 2022‎ 2405:6580:a840:8d00:7685:2aff:fe1a:ccd9 talk‎ 25,986 bytes +608‎ Add Fuzzy Rule Interpolation as another possible function approximator undo Tag: Visual edit

6 April 2024

3 April 2024

4 January 2024

25 December 2023

15 December 2023

6 December 2023

5 December 2023

1 December 2023

29 November 2023

27 October 2023

22 October 2023

24 August 2023

25 July 2023

29 May 2023

10 May 2023

21 April 2023

20 April 2023

19 April 2023

11 April 2023

4 April 2023

28 March 2023

22 March 2023

20 February 2023

26 January 2023

18 November 2022

8 November 2022

22 October 2022

8 October 2022

30 September 2022

14 August 2022

16 July 2022

26 June 2022

26 May 2022

25 May 2022