Affectively Framework: Towards Human-like Affect-Based Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916336991469568 |
|---|---|
| author | Barthet, Matthew Gallotta, Roberto Khalifa, Ahmed Liapis, Antonios Yannakakis, Georgios N. |
| author_facet | Barthet, Matthew Gallotta, Roberto Khalifa, Ahmed Liapis, Antonios Yannakakis, Georgios N. |
| contents | Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human affect models as part of their observation space or reward mechanism. To address this, we present the \emph{Affectively Framework}, a set of Open-AI Gym environments that integrate affect as part of the observation space. This paper introduces the framework and its three game environments and provides baseline experiments to validate its effectiveness and potential. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18316 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Affectively Framework: Towards Human-like Affect-Based Agents Barthet, Matthew Gallotta, Roberto Khalifa, Ahmed Liapis, Antonios Yannakakis, Georgios N. Artificial Intelligence Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human affect models as part of their observation space or reward mechanism. To address this, we present the \emph{Affectively Framework}, a set of Open-AI Gym environments that integrate affect as part of the observation space. This paper introduces the framework and its three game environments and provides baseline experiments to validate its effectiveness and potential. |
| title | Affectively Framework: Towards Human-like Affect-Based Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.18316 |