Asymmetric Norms to Approximate the Minimum Action Distance
- URL: http://arxiv.org/abs/2312.10276v2
- Date: Tue, 19 Dec 2023 08:12:51 GMT
- Title: Asymmetric Norms to Approximate the Minimum Action Distance
- Authors: Lorenzo Steccanella, Anders Jonsson
- Abstract summary: This paper presents a state representation for reward-free Markov decision processes.
We show how this representation can be leveraged to learn goal-conditioned policies.
- Score: 9.040428950629153
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper presents a state representation for reward-free Markov decision
processes. The idea is to learn, in a self-supervised manner, an embedding
space where distances between pairs of embedded states correspond to the
minimum number of actions needed to transition between them. Unlike previous
methods, our approach incorporates an asymmetric norm parametrization, enabling
accurate approximations of minimum action distances in environments with
inherent asymmetry. We show how this representation can be leveraged to learn
goal-conditioned policies, providing a notion of similarity between states and
goals and a useful heuristic distance to guide planning. To validate our
approach, we conduct empirical experiments on both symmetric and asymmetric
environments. Our results show that our asymmetric norm parametrization
performs comparably to symmetric norms in symmetric environments and surpasses
symmetric norms in asymmetric environments.
Related papers
- How much symmetry do symmetric measurements need for efficient operational applications? [0.0]
For informationally complete sets, we propose construction methods from orthonormal Hermitian operator bases.
Some of the symmetry properties, lost in the process of generalization, can be recovered without fixing the same number of elements for all POVMs.
arXiv Detail & Related papers (2024-04-02T15:23:08Z) - Equivariant Symmetry Breaking Sets [0.6475999521931204]
Equivariant neural networks (ENNs) have been shown to be extremely effective in applications involving underlying symmetries.
We propose a novel symmetry breaking framework that is fully equivariant and is the first which fully addresses spontaneous symmetry breaking.
arXiv Detail & Related papers (2024-02-05T02:35:11Z) - Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries [11.54837584979607]
Group equivariance can overly constrain models if the symmetries in the group differ from those observed in data.
We propose a method able to detect the level of symmetry of each input without the need for labels.
Our framework is general enough to accommodate different families of both continuous and discrete symmetry distributions.
arXiv Detail & Related papers (2023-12-19T15:11:46Z) - Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation [49.67011673289242]
This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a smooth manifold.
It induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure.
arXiv Detail & Related papers (2023-11-08T15:17:13Z) - Regularizing Towards Soft Equivariance Under Mixed Symmetries [23.603875905608565]
We present a regularizer-based method for building a model for a dataset with mixed approximate symmetries.
We show that our method achieves better accuracy than prior approaches while discovering the approximate symmetry levels correctly.
arXiv Detail & Related papers (2023-06-01T05:33:41Z) - Evaluating the Robustness of Interpretability Methods through
Explanation Invariance and Equivariance [72.50214227616728]
Interpretability methods are valuable only if their explanations faithfully describe the explained model.
We consider neural networks whose predictions are invariant under a specific symmetry group.
arXiv Detail & Related papers (2023-04-13T17:59:03Z) - On the Importance of Asymmetry for Siamese Representation Learning [53.86929387179092]
Siamese networks are conceptually symmetric with two parallel encoders.
We study the importance of asymmetry by explicitly distinguishing the two encoders within the network.
We find the improvements from asymmetric designs generalize well to longer training schedules, multiple other frameworks and newer backbones.
arXiv Detail & Related papers (2022-04-01T17:57:24Z) - Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space.
We establish non-asymptotic bounds for both the operator defect and the estimation error.
arXiv Detail & Related papers (2022-01-21T02:46:57Z) - GELATO: Geometrically Enriched Latent Model for Offline Reinforcement
Learning [54.291331971813364]
offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods.
In this work, we demonstrate the benefit of combining the two in a latent variational model.
Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
arXiv Detail & Related papers (2021-02-22T19:42:40Z) - The Advantage of Conditional Meta-Learning for Biased Regularization and
Fine-Tuning [50.21341246243422]
Biased regularization and fine-tuning are two recent meta-learning approaches.
We propose conditional meta-learning, inferring a conditioning function mapping task's side information into a meta- parameter vector.
We then propose a convex meta-algorithm providing a comparable advantage also in practice.
arXiv Detail & Related papers (2020-08-25T07:32:16Z) - The quantum marginal problem for symmetric states: applications to
variational optimization, nonlocality and self-testing [0.0]
We present a method to solve the quantum marginal problem for symmetric $d$-level systems.
We illustrate the applicability of the method in central quantum information problems with several exemplary case studies.
arXiv Detail & Related papers (2020-01-13T18:20:53Z)
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.