Skip to main content
Data Science

Timeline for How to predict advantage value in deep reinforcement learning

Current License: CC BY-SA 4.0

15 events
when toggle format what by license comment
Nov 11 at 17:04 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Jul 13 at 20:00 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Mar 12 at 8:00 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Nov 10, 2023 at 8:01 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Jul 12, 2023 at 16:04 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Jun 10, 2023 at 8:17 answer added Luca Anzalone timeline score: 0
Nov 29, 2021 at 14:26 history edited Brian Spiering CC BY-SA 4.0
edited title
May 18, 2021 at 11:54 review Suggested edits
May 19, 2021 at 12:32
S May 18, 2021 at 9:36 history suggested Shayan Shafiq CC BY-SA 4.0
Edited tags, fixed hyperlink
May 17, 2021 at 22:50 review Suggested edits
S May 18, 2021 at 9:36
May 16, 2021 at 17:33 review Close votes
May 18, 2021 at 4:27
Jun 8, 2018 at 7:38 comment added lhk @NeilSlater, oh that makes sense. Perfect counterargument for this idea that max(advantage) = value.
Jun 8, 2018 at 6:56 comment added Neil Slater Re: "I read somewhere that the maximum advantage is the value". The maximum advantage in an optimised system (where Q and V calculate values for the optimal policy) is zero.
Jun 7, 2018 at 23:09 review First posts
Jun 8, 2018 at 12:44
Jun 7, 2018 at 23:05 history asked lhk CC BY-SA 4.0