Timeline for How to deal with episode termination in Advantage Actor-Critic algorithm?
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 3, 2018 at 2:57 | comment | added | Aleksei Petrenko | Thank you for your answer! Basically you're suggesting to give the value of the timer to the agent as an additional input, and I agree with you, this seems like a very reasonable thing to do. To my surprise, the majority of existing RL algorithms do not bother with that. | |
| Nov 28, 2018 at 2:58 | history | edited | Douglas Daseeco | CC BY-SA 4.0 |
Correct proportional statement.
|
| Nov 27, 2018 at 8:15 | history | answered | Douglas Daseeco | CC BY-SA 4.0 |