Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2403.03141 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911789587890176 |
|---|---|
| author | Golchha, Hitesh Yerawar, Sahil Patel, Dhruvesh Dan, Soham Murugesan, Keerthiram |
| author_facet | Golchha, Hitesh Yerawar, Sahil Patel, Dhruvesh Dan, Soham Murugesan, Keerthiram |
| contents | Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al.,2022), a challenging text environment, LGE outperforms vanilla RL agents significantly and also outperforms other sophisticated methods like Behaviour Cloning and Text Decision Transformer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03141 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Language Guided Exploration for RL Agents in Text Environments Golchha, Hitesh Yerawar, Sahil Patel, Dhruvesh Dan, Soham Murugesan, Keerthiram Computation and Language Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al.,2022), a challenging text environment, LGE outperforms vanilla RL agents significantly and also outperforms other sophisticated methods like Behaviour Cloning and Text Decision Transformer. |
| title | Language Guided Exploration for RL Agents in Text Environments |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.03141 |