Timeline for Solving Highly Stochastic Environments Using Reinforcement Learning
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 23 at 18:53 | comment | added | Neil Slater | Do you know the state transition rules and/or reward distribution in advance. I.e. is there a way for you to use a model-based approach? Also, are you able to run this environment quickly in simulation, or need to rely on interactions with a realtime environment? Another way to put this - are you looking for sample-efficiency or computational efficiency? | |
| Sep 23 at 17:26 | history | asked | PJORR | CC BY-SA 4.0 |