paper-with-me

홈 › Papers

Proper Laplacian Representation Learning

2023-10-16 · Diego Gomez, Michael Bowling, Marlos C. Machado

The ability to learn good representations of states is essential for solving large reinforcement learning problems, where exploration, generalization, and transfer are particularly challenging. The Laplacian representation is a promising approach to address these problems by inducing informative state encoding and intrinsic rewards for temporally-extended action discovery and reward shaping. To obtain the Laplacian representation one needs to compute the eigensystem of the graph Laplacian, which is often approximated through optimization objectives compatible with deep learning approaches. These approximations, however, depend on hyperparameters that are impossible to tune efficiently, converge to arbitrary rotations of the desired eigenvectors, and are unable to accurately recover the corresponding eigenvalues. In this paper we introduce a theoretically sound objective and corresponding optimization algorithm for approximating the Laplacian representation. Our approach naturally recovers both the true eigenvectors and eigenvalues while eliminating the hyperparameter dependence of previous approximations. We provide theoretical guarantees for our method and we show that those results translate empirically into robust learning across multiple environments.

📄 PDF Abstract BibTeX arXiv:2310.10833

Code (2)

tarod13/laplacian_dual_dynamics 공식 구현 jax
mklissa/dceo jax

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

GLEE: Geometric Laplacian Eigenmap Embedding

2019-05-23 · Leo Torres, Kevin S. Chan, Tina Eliassi-Rad

Graph embedding seeks to build a low-dimensional representation of a graph G. This low-dimensional representation is then used for various downstream tasks. One popular approach is Laplacian Eigenmaps, which constructs a…

Graph EmbeddingGraph ReconstructionLink Prediction

Reachability-Aware Laplacian Representation in Reinforcement Learning

2022-10-24 · Kaixin Wang, Kuangqi Zhou, Jiashi Feng, Bryan Hooi 외

In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment. A desirable property of LapRep stated in prior works is that the Euc…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation

2025-08-18 · Haruka Ezoe, Hiroki Matsumoto, Ryohei Hisano arxiv

Dynamic relational data arise in many machine learning applications, yet their evolving structure poses challenges for learning representations that remain consistent and interpretable over time. A common approach is to …

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

2024-10-13 · Junru Zhou, Cai Zhou, Xiyuan Wang, Pan Li 외

Graph neural networks (GNNs) have achieved remarkable success in a variety of machine learning tasks over graph data. Existing GNNs usually rely on message passing, i.e., computing node representations by gathering infor…

Graph Learning

On the properties of Laplacian pseudoinverses

2021-09-29 · Angela Fontan, Claudio Altafini

The pseudoinverse of a graph Laplacian is used in many applications and fields, such as for instance in the computation of the effective resistance in electrical networks, in the calculation of the hitting/commuting time…