Timeline for What does the Reward function depend on in a Markov Decision Processes (MDPs), in the context of Reinforcement Learning?
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 12, 2023 at 15:06 | comment | added | Rémy Hosseinkhan Boucher | This is ok when $T$ is a function, while it is less direct in the case of $T$ being a markovian kernel.. | |
| Apr 20, 2019 at 17:17 | history | answered | czxttkl | CC BY-SA 4.0 |