Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914863837609984 |
|---|---|
| author | Gallouédec, Quentin Beeching, Edward Romac, Clément Dellandréa, Emmanuel |
| author_facet | Gallouédec, Quentin Beeching, Edward Romac, Clément Dellandréa, Emmanuel |
| contents | The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research. The prevailing methodology in Reinforcement Learning (RL) typically limits models to a single task within a unimodal framework, a limitation that contrasts with the broader vision of a versatile, multi-domain model. In this paper, we present Jack of All Trades (JAT), a transformer-based model with a unique design optimized for handling sequential decision-making tasks and multi-modal data types. The JAT model demonstrates its robust capabilities and versatility by achieving strong performance on very different RL benchmarks, along with promising results on Computer Vision (CV) and Natural Language Processing (NLP) tasks, all using a single set of weights. The JAT model marks a significant step towards more general, cross-domain AI model design, and notably, it is the first model of its kind to be fully open-sourced at https://huggingface.co/jat-project/jat, including a pioneering general-purpose dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09844 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent Gallouédec, Quentin Beeching, Edward Romac, Clément Dellandréa, Emmanuel Artificial Intelligence The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research. The prevailing methodology in Reinforcement Learning (RL) typically limits models to a single task within a unimodal framework, a limitation that contrasts with the broader vision of a versatile, multi-domain model. In this paper, we present Jack of All Trades (JAT), a transformer-based model with a unique design optimized for handling sequential decision-making tasks and multi-modal data types. The JAT model demonstrates its robust capabilities and versatility by achieving strong performance on very different RL benchmarks, along with promising results on Computer Vision (CV) and Natural Language Processing (NLP) tasks, all using a single set of weights. The JAT model marks a significant step towards more general, cross-domain AI model design, and notably, it is the first model of its kind to be fully open-sourced at https://huggingface.co/jat-project/jat, including a pioneering general-purpose dataset. |
| title | Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2402.09844 |