MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

• URL: http://arxiv.org/abs/2407.15086v1
• Date: Sun, 21 Jul 2024 07:56:48 GMT
• Title: MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery
• Authors: Pei Zhou, Yanchao Yang,
• Abstract summary: We introduce an information-theoretic criterion to characterize the regularities that signify a set of physical states. We develop a framework that trains a concept discovery network using this criterion.
• Score: 8.98306885751389
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We aim to discover manipulation concepts embedded in the unannotated demonstrations, which are recognized as key physical states. The discovered concepts can facilitate training manipulation policies and promote generalization. Current methods relying on multimodal foundation models for deriving key states usually lack accuracy and semantic consistency due to limited multimodal robot data. In contrast, we introduce an information-theoretic criterion to characterize the regularities that signify a set of physical states. We also develop a framework that trains a concept discovery network using this criterion, thus bypassing the dependence on human semantics and alleviating costly human labeling. The proposed criterion is based on the observation that key states, which deserve to be conceptualized, often admit more physical constraints than non-key states. This phenomenon can be formalized as maximizing the mutual information between the putative key state and its preceding state, i.e., Maximal Mutual Information (MaxMI). By employing MaxMI, the trained key state localization network can accurately identify states of sufficient physical significance, exhibiting reasonable semantic compatibility with human perception. Furthermore, the proposed framework produces key states that lead to concept-guided manipulation policies with higher success rates and better generalization in various robotic tasks compared to the baselines, verifying the effectiveness of the proposed criterion.

Related papers

• Evaluating Readability and Faithfulness of Concept-based Explanations [35.48852504832633]
  Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by Large Language Models. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging.
  arXiv  Detail & Related papers  (2024-04-29T09:20:25Z)
• InfoCon: Concept Discovery with Generative and Discriminative Informativeness [7.160037417413006]
  We focus on the self-supervised discovery of manipulation concepts that can be adapted and reassembled to address various robotic tasks. We model manipulation concepts as generative and discriminative goals and derive metrics that can autonomously link them to meaningful sub-trajectories.
  arXiv  Detail & Related papers  (2024-03-14T14:14:04Z)
• Enhancing Actionable Formal Concept Identification with Base-Equivalent Conceptual-Relevance [0.0]
  We introduce the Base-Equivalent Conceptual Relevance (BECR) score, a novel conceptual relevance interestingness measure for improving the identification of actionable concepts. The basic idea of BECR is that the more base and equivalent attributes and minimal generators a concept intent has, the more relevant it is. Preliminary experiments on synthetic and real-world datasets show the efficiency of BECR compared to the well-known stability index.
  arXiv  Detail & Related papers  (2023-12-22T03:57:40Z)
• Reasoning with the Theory of Mind for Pragmatic Semantic Communication [62.87895431431273]
  A pragmatic semantic communication framework is proposed in this paper. It enables effective goal-oriented information sharing between two-intelligent agents. Numerical evaluations demonstrate the framework's ability to achieve efficient communication with a reduced amount of bits.
  arXiv  Detail & Related papers  (2023-11-30T03:36:19Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• Understanding Masked Autoencoders via Hierarchical Latent Variable Models [109.35382136147349]
  Masked autoencoder (MAE) has recently achieved prominent success in a variety of vision tasks. Despite the emergence of intriguing empirical observations on MAE, a theoretically principled understanding is still lacking.
  arXiv  Detail & Related papers  (2023-06-08T03:00:10Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
  We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
  arXiv  Detail & Related papers  (2022-06-08T04:09:13Z)
• The Geometry of Robust Value Functions [119.94715309072983]
  We introduce a new perspective that enables us to characterize both the non-robust and robust value space. We show that the robust value space is determined by a set conic hypersurfaces, each which contains the robust values of all policies that agree on one state.
  arXiv  Detail & Related papers  (2022-01-30T22:12:17Z)
• Detecting Important Patterns Using Conceptual Relevance Interestingness Measure [0.0]
  We introduce the Conceptual Relevance (CR) score, a new scalable interestingness measurement for the identification of actionable concepts. From a conceptual perspective, the minimal generators provide key information about their associated concept intent. As such, the CR index quantifies both the amount of conceptually relevant attributes and the number of the minimal generators per concept intent.
  arXiv  Detail & Related papers  (2021-10-21T16:45:01Z)
• Metrics and continuity in reinforcement learning [34.10996560464196]
  We introduce a unified formalism for defining topologies through the lens of metrics. We establish a hierarchy amongst these metrics and demonstrate their theoretical implications on the Markov Decision Process. We complement our theoretical results with empirical evaluations showcasing the differences between the metrics considered.
  arXiv  Detail & Related papers  (2021-02-02T14:30:41Z)

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.