Learning to Model the World with Language
- URL: http://arxiv.org/abs/2308.01399v2
- Date: Fri, 31 May 2024 15:32:02 GMT
- Title: Learning to Model the World with Language
- Authors: Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan,
- Abstract summary: To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world.
Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future.
We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations.
- Score: 100.76069091703505
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language -- language like "this button turns on the TV" or "I put the bowls away" -- that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future: what they will observe, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations, and learns to act from imagined model rollouts. While current methods that learn language-conditioned policies degrade in performance with more diverse types of language, we show that Dynalang learns to leverage environment descriptions, game rules, and instructions to excel on tasks ranging from game-playing to navigating photorealistic home scans. Finally, we show that our method enables additional capabilities due to learning a generative model: Dynalang can be pretrained on text-only data, enabling learning from offline datasets, and generate language grounded in an environment.
Related papers
- Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use [16.425032085699698]
It is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks.
It's not clear how to incorporate rich language use to facilitate task learning.
This paper studies different types of language inputs in facilitating reinforcement learning.
arXiv Detail & Related papers (2024-10-31T17:59:52Z) - Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling [47.7950860342515]
LexiContrastive Grounding (LCG) is a grounded language learning procedure that leverages visual supervision to improve textual representations.
LCG outperforms standard language-only models in learning efficiency.
It improves upon vision-and-language learning procedures including CLIP, GIT, Flamingo, and Vokenization.
arXiv Detail & Related papers (2024-03-21T16:52:01Z) - Video as the New Language for Real-World Decision Making [100.68643056416394]
Video data captures important information about the physical world that is difficult to express in language.
Video can serve as a unified interface that can absorb internet knowledge and represent diverse tasks.
We identify major impact opportunities in domains such as robotics, self-driving, and science.
arXiv Detail & Related papers (2024-02-27T02:05:29Z) - Visual Grounding Helps Learn Word Meanings in Low-Data Regimes [47.7950860342515]
Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension.
But to achieve these results, LMs must be trained in distinctly un-human-like ways.
Do models trained more naturalistically -- with grounded supervision -- exhibit more humanlike language learning?
We investigate this question in the context of word learning, a key sub-task in language acquisition.
arXiv Detail & Related papers (2023-10-20T03:33:36Z) - Accessible Instruction-Following Agent [0.0]
We introduce UVLN, a novel machine-translation instructional augmented framework for cross-lingual vision-language navigation.
We extend the standard VLN training objectives to a multilingual setting via a cross-lingual language encoder.
Experiments over Room Across Room dataset prove the effectiveness of our approach.
arXiv Detail & Related papers (2023-05-08T23:57:26Z) - Language-Driven Representation Learning for Robotics [115.93273609767145]
Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks.
We introduce a framework for language-driven representation learning from human videos and captions.
We find that Voltron's language-driven learning outperform the prior-of-the-art, especially on targeted problems requiring higher-level control.
arXiv Detail & Related papers (2023-02-24T17:29:31Z) - Robotic Skill Acquisition via Instruction Augmentation with
Vision-Language Models [70.82705830137708]
We introduce Data-driven Instruction Augmentation for Language-conditioned control (DIAL)
We utilize semi-language labels leveraging the semantic understanding of CLIP to propagate knowledge onto large datasets of unlabelled demonstration data.
DIAL enables imitation learning policies to acquire new capabilities and generalize to 60 novel instructions unseen in the original dataset.
arXiv Detail & Related papers (2022-11-21T18:56:00Z) - Do As I Can, Not As I Say: Grounding Language in Robotic Affordances [119.29555551279155]
Large language models can encode a wealth of semantic knowledge about the world.
Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language.
We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions.
arXiv Detail & Related papers (2022-04-04T17:57:11Z) - Vokenization: Improving Language Understanding with Contextualized,
Visual-Grounded Supervision [110.66085917826648]
We develop a technique that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images.
"vokenization" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora.
Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks.
arXiv Detail & Related papers (2020-10-14T02:11:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.