Rezultati
eNauka >
Results >
Benefits of Using LLM for Long-Term Planning with Distilled Subtask Model Compared to End-to-End Reinforcement Learning in the MiniGrid Simulator
| Title: | Benefits of Using LLM for Long-Term Planning with Distilled Subtask Model Compared to End-to-End Reinforcement Learning in the MiniGrid Simulator | Authors: | Pluskoski, Aleksandar; Ciganovic, Igor; Jovanovic, Milos; Vasiljevic, Jelena | Issue Date: | 2026 | Publication: | ELECTRONICS | ISSN: | 2079-9292 Electronics (Basel) Search Idenfier |
Type: | Article | Collation: | vol. 15 br. 9 str. 1921-1921 | DOI: | 10.3390/electronics15091921 | WoS-ID: | 001763538200001 | Scopus-ID: | 2-s2.0-105038405138 | URI: | https://enauka.gov.rs/handle/123456789/1039654 | Metadata source: | (Preuzeto iz Nasi u WoS) | M-category: | 22M22 |
Rezultati na eNauka su zaštićeni autorskim pravima i sva prava su zadržana, osim ako nije drugačije naznačeno.