Timeline for Appropriate algorithm for RL problem with sparse rewards, continuous actions and significant stochasticity
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 18, 2023 at 17:52 | comment | added | adeleye ifeoluwa seun | Use Introduction Multi agent sysrtem | |
| Apr 26, 2020 at 3:42 | answer | added | Huan | timeline score: 4 | |
| Apr 23, 2020 at 10:43 | comment | added | BGa | The optimization problem I'm trying to solve has been approximated analytically - the approximation to the optimal solution depends on three variables (t-remaining time, q-current inventory and s-current price). It is precisely those variables that I've included in my state space. Therefore, RL should in theory be able to learn this function, provided enough episodes and an NN function approximator with enough capacity. | |
| Apr 23, 2020 at 10:37 | comment | added | Neil Slater | You seem to be using the right kind of algorithm (I would think that most policy gradient methods could at least be applied here, although some may perform better than others). Your problem may well be intractable though. Do you have any evidence that it is solvable given the state data you are using? | |
| Apr 23, 2020 at 9:39 | history | asked | BGa | CC BY-SA 4.0 |