Difference between revisions of "AlfWorld"
m |
m |
||
| (9 intermediate revisions by the same user not shown) | |||
| Line 14: | Line 14: | ||
* [https://arxiv.org/abs/2010.03768 AlfWorld: Aligning Text and Embodied Environments for Interactive Learning | M. Shridhar, X. Yuan, M. Côté, Y. Bisk, A. Trischler, M. Hausknecht - arXiv] | * [https://arxiv.org/abs/2010.03768 AlfWorld: Aligning Text and Embodied Environments for Interactive Learning | M. Shridhar, X. Yuan, M. Côté, Y. Bisk, A. Trischler, M. Hausknecht - arXiv] | ||
* [https://github.com/alfworld/alfworld AlfWorld | GitHub] | * [https://github.com/alfworld/alfworld AlfWorld | GitHub] | ||
| − | |||
| − | |||
| − | <b>AlfWorld</b>: Aligning Text and Embodied Environments for Interactive Learning. | + | * [[ALFRED]] ... Action Learning From Realistic Environments and Directives |
| + | * [[Agents]] ... [[Robotic Process Automation (RPA)|Robotic Process Automation]] ... [[Assistants]] ... [[Personal Companions]] ... [[Personal Productivity|Productivity]] ... [[Email]] ... [[Negotiation]] ... [[LangChain]] | ||
| + | * [[Artificial General Intelligence (AGI) to Singularity]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]] | ||
| + | * [[Embodied AI]] | ||
| + | |||
| + | <b>AlfWorld</b>: Aligning Text and [[Embodied AI]] Environments for Interactive Learning. a simulator that enables agents to learn abstract, text based policies in TextWorld (Côté et al., 2018) and then execute goals from the [[ALFRED]] benchmark (Shridhar et al., 2020) in a rich visual environment. ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions. In turn, as we demonstrate empirically, this fosters better agent generalization than training only in the visually grounded environment. BUTLER's simple, modular design factors the problem to allow researchers to focus on models for improving every piece of the pipeline (language understanding, planning, navigation, and visual scene understanding). The aligned environments allow agents to reason and learn high-level policies in an abstract space before solving embodied tasks through low-level actuation. | ||
<img src="https://github.com/alfworld/alfworld/raw/master/media/alfworld_teaser.png" width="600"> | <img src="https://github.com/alfworld/alfworld/raw/master/media/alfworld_teaser.png" width="600"> | ||
| + | |||
| + | |||
| + | <youtube>Iu2S1wWJ2T4</youtube> | ||
Latest revision as of 08:35, 23 March 2024
Youtube ... Quora ...Google search ...Google News ...Bing News
- AlfWorld: Aligning Text and Embodied Environments for Interactive Learning | M. Shridhar, X. Yuan, M. Côté, Y. Bisk, A. Trischler, M. Hausknecht - arXiv
- AlfWorld | GitHub
- ALFRED ... Action Learning From Realistic Environments and Directives
- Agents ... Robotic Process Automation ... Assistants ... Personal Companions ... Productivity ... Email ... Negotiation ... LangChain
- Artificial General Intelligence (AGI) to Singularity ... Curious Reasoning ... Emergence ... Moonshots ... Explainable AI ... Automated Learning
- Embodied AI
AlfWorld: Aligning Text and Embodied AI Environments for Interactive Learning. a simulator that enables agents to learn abstract, text based policies in TextWorld (Côté et al., 2018) and then execute goals from the ALFRED benchmark (Shridhar et al., 2020) in a rich visual environment. ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions. In turn, as we demonstrate empirically, this fosters better agent generalization than training only in the visually grounded environment. BUTLER's simple, modular design factors the problem to allow researchers to focus on models for improving every piece of the pipeline (language understanding, planning, navigation, and visual scene understanding). The aligned environments allow agents to reason and learn high-level policies in an abstract space before solving embodied tasks through low-level actuation.
