paper-with-me

홈 › Papers

Probabilistic World Modeling with Asymmetric Distance Measure

2024-03-16 · Meng Song

Representation learning is a fundamental task in machine learning, aiming at uncovering structures from data to facilitate subsequent tasks. However, what is a good representation for planning and reasoning in a stochastic world remains an open problem. In this work, we posit that learning a distance function is essential to allow planning and reasoning in the representation space. We show that a geometric abstraction of the probabilistic world dynamics can be embedded into the representation space through asymmetric contrastive learning. Unlike previous approaches that focus on learning mutual similarity or compatibility measures, we instead learn an asymmetric similarity function that reflects the state reachability and allows multi-way probabilistic inference. Moreover, by conditioning on a common reference state (e.g. the observer's current state), the learned representation space allows us to discover the geometrically salient states that only a handful of paths can lead through. These states can naturally serve as subgoals to break down long-horizon planning tasks. We evaluate our method in gridworld environments with various layouts and demonstrate its effectiveness in discovering the subgoals.

📄 PDF Abstract BibTeX arXiv:2403.10875

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Taming the Long Tail of Deep Probabilistic Forecasting

2022-02-27 · Jedrzej Kozerawski, Mayank Sharan, Rose Yu

Deep probabilistic forecasting is gaining attention in numerous applications ranging from weather prognosis, through electricity consumption estimation, to autonomous vehicle trajectory prediction. However, existing appr…

PrognosisTime SeriesTime Series AnalysisTrajectory Prediction

Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation

2021-01-13 · Chen Ma, Liheng Ma, Yingxue Zhang, Ruiming Tang 외

Personalized recommender systems are playing an increasingly important role as more content and services become available and users struggle to identify what might interest them. Although matrix factorization and deep le…

Metric LearningRecommendation Systems

Bregman-Hausdorff divergence: strengthening the connections between computational geometry and machine learning

2025-04-09 · Tuyen Pham, Hana Dal Poz Kouřimská, Hubert Wagner

The purpose of this paper is twofold. On a technical side, we propose an extension of the Hausdorff distance from metric spaces to spaces equipped with asymmetric distance measures. Specifically, we focus on the family o…

An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

2020-02-14 · ICLR 2020 1 · Silviu Pitis, Harris Chan, Kiarash Jamali, Jimmy Ba

Distances are pervasive in machine learning. They serve as similarity measures, loss functions, and learning targets; it is said that a good distance measure solves a task. When defining distances, the triangle inequalit…

Inductive BiasMetric LearningMulti-Goal Reinforcement Learningreinforcement-learning+2

RADAR: Learning to Route with Asymmetry-aware DistAnce Representations

2026-03-03 · Hang Yi, Ziwei Huang, Yining Ma, Zhiguang Cao arxiv

Recent neural solvers have achieved strong performance on vehicle routing problems (VRPs), yet they mainly assume symmetric Euclidean distances, restricting applicability to real-world scenarios. A core challenge is enco…