DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

• URL: http://arxiv.org/abs/2402.18137v2
• Date: Fri, 24 May 2024 03:31:50 GMT
• Title: DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
• Authors: Jianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao, Xiao Hu, Sijie Cheng, Haoyi Niu, Jihao Liu, Yu Liu, Jingjing Liu, Ya-Qin Zhang, Xianyuan Zhan,
• Abstract summary: Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots. We propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences. DecisionNCE provides an embodied representation learning framework that elegantly extracts both local and global task progression features.
• Score: 27.705230758809094
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/

Related papers

• Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics [25.2461925479135]
  Video-Language Critic is a reward model that can be trained on readily available cross-embodiment data. Our model enables 2x more sample-efficient policy training on Meta-World tasks than a sparse reward only.
  arXiv  Detail & Related papers  (2024-05-30T12:18:06Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• MaPLe: Multi-modal Prompt Learning [54.96069171726668]
  We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
  arXiv  Detail & Related papers  (2022-10-06T17:59:56Z)
• Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations [25.33452947179541]
  We show the effectiveness of object-aware representation learning techniques for robotic tasks. Our model learns control policies in a sample-efficient manner and outperforms state-of-the-art object techniques.
  arXiv  Detail & Related papers  (2022-05-12T19:48:11Z)
• Pre-Trained Language Models for Interactive Decision-Making [72.77825666035203]
  We describe a framework for imitation learning in which goals and observations are represented as a sequence of embeddings. We demonstrate that this framework enables effective generalization across different environments. For test tasks involving novel goals or novel scenes, initializing policies with language models improves task completion rates by 43.6%.
  arXiv  Detail & Related papers  (2022-02-03T18:55:52Z)
• CLIPort: What and Where Pathways for Robotic Manipulation [35.505615833638124]
  We present CLIPort, a language-conditioned imitation-learning agent that combines the broad semantic understanding with the spatial precision of Transporter. Our framework is capable of solving a variety of language-specified tabletop tasks without any explicit representations of object poses, instance segmentations, memory, symbolic states, or syntactic structures.
  arXiv  Detail & Related papers  (2021-09-24T17:44:28Z)
• Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition [80.446770909975]
  Linguistic knowledge is of great benefit to scene text recognition. How to effectively model linguistic rules in end-to-end deep networks remains a research challenge. We propose an autonomous, bidirectional and iterative ABINet for scene text recognition.
  arXiv  Detail & Related papers  (2021-03-11T06:47:45Z)
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning [66.9937776799536]
  The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments. We propose a cross-modal grounding module to equip the agent with a better ability to track the correspondence between the textual and visual modalities.
  arXiv  Detail & Related papers  (2020-11-22T09:13:46Z)
• Following Instructions by Imagining and Reaching Visual Goals [8.19944635961041]
  We present a novel framework for learning to perform temporally extended tasks using spatial reasoning. Our framework operates on raw pixel images, assumes no prior linguistic or perceptual knowledge, and learns via intrinsic motivation. We validate our method in two environments with a robot arm in a simulated interactive 3D environment.
  arXiv  Detail & Related papers  (2020-01-25T23:26:56Z)

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.