Policy Return: A New Method for Reducing the Number of Experimental Trials in Deep Reinforcement Learning
Using the same algorithm and hyperparameter configurations, deep reinforcement learning (DRL) will derive drastically different results from multiple experimental trials, and most of these results are unsatisfactory. Because of the instability of the results, researchers have to perform many trials...
Zapisane w:
| Główni autorzy: | , , |
|---|---|
| Format: | Artigo |
| Język: | Inglês |
| Wydane: |
IEEE
2020-01-01
|
| Seria: | IEEE Access |
| Hasła przedmiotowe: | |
| Dostęp online: | https://ieeexplore.ieee.org/document/9298771/ |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|