Timeline for Semi-gradient TD(0) Choosing an Action
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 28, 2017 at 17:14 | comment | added | zimmerrol | I asked a new, seperate question - maybe you can give me there more details. stackoverflow.com/questions/45377404/… | |
| Jul 25, 2017 at 15:29 | comment | added | Neil Slater | @flashtek That is a different question, why not ask it. There are two main options. But essentially you must make the estimate s before you can take the max. | |
| Jul 25, 2017 at 11:12 | comment | added | zimmerrol |
How can one choose the argmax of q using a neural network as a representation of q?
|
|
| Apr 9, 2017 at 10:37 | vote | accept | end1dream | ||
| Apr 7, 2017 at 9:01 | history | edited | Neil Slater | CC BY-SA 3.0 |
added 691 characters in body
|
| Apr 6, 2017 at 21:17 | history | edited | Neil Slater | CC BY-SA 3.0 |
added 10 characters in body
|
| Apr 6, 2017 at 20:58 | history | edited | Neil Slater | CC BY-SA 3.0 |
added 58 characters in body
|
| Apr 6, 2017 at 20:47 | history | answered | Neil Slater | CC BY-SA 3.0 |