elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912477187407872 |
|---|---|
| author | Osborne, Philip Carvalho, Danilo S. Freitas, André |
| author_facet | Osborne, Philip Carvalho, Danilo S. Freitas, André |
| contents | We present elsciRL, an open-source Python library to facilitate the application of language solutions on reinforcement learning problems. We demonstrate the potential of our software by extending the Language Adapter with Self-Completing Instruction framework defined in (Osborne, 2024) with the use of LLMs. Our approach can be re-applied to new applications with minimal setup requirements. We provide a novel GUI that allows a user to provide text input for an LLM to generate instructions which it can then self-complete. Empirical results indicate that these instructions \textit{can} improve a reinforcement learning agent's performance. Therefore, we present this work to accelerate the evaluation of language solutions on reward based environments to enable new opportunities for scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08705 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings Osborne, Philip Carvalho, Danilo S. Freitas, André Artificial Intelligence I.2.5; I.2.1; I.2.7; I.2.11 We present elsciRL, an open-source Python library to facilitate the application of language solutions on reinforcement learning problems. We demonstrate the potential of our software by extending the Language Adapter with Self-Completing Instruction framework defined in (Osborne, 2024) with the use of LLMs. Our approach can be re-applied to new applications with minimal setup requirements. We provide a novel GUI that allows a user to provide text input for an LLM to generate instructions which it can then self-complete. Empirical results indicate that these instructions \textit{can} improve a reinforcement learning agent's performance. Therefore, we present this work to accelerate the evaluation of language solutions on reward based environments to enable new opportunities for scientific discovery. |
| title | elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings |
| topic | Artificial Intelligence I.2.5; I.2.1; I.2.7; I.2.11 |
| url | https://arxiv.org/abs/2507.08705 |