PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning

• URL: http://arxiv.org/abs/2607.18004v1
• Date: Mon, 20 Jul 2026 14:36:11 GMT
• Title: PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
• Abstract summary: We introduce **PAMD: Pairwise Adaptive Mahalanobis Distance**, which parameterizes a positive-definite, pair-conditioned metric for measuring latent state similarity.<n>We empirically validate our method on visual MuJoCo continuous-control tasks, where final performance of several recent bi-based RL algorithms is substantially improved when equipped with the distance we propose.
• Score: 1.7434507809930746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many visual reinforcement learning (RL) algorithms learn representations by matching latent distances to a behavioral distance induced by reward and transition similarity. In practice, the choice of the latent distance can strongly affect performance: using a fixed, pre-specified global norms (e.g., $\ell_p$ norms or other hand-designed metrics) may be overly restrictive to capture the behavioral distance. In contrast, unconstrained pairwise distances may admit degenerate solutions that drive the metric loss down without improving the representation. To address this gap, we introduce **PAMD: Pairwise Adaptive Mahalanobis Distance**, which parameterizes a positive-definite, pair-conditioned metric for measuring latent state similarity. PAMD is a simple plug-in for existing bisimulation-based methods, offering a more expressive yet structured alternative to fixed, pre-specified latent distances. We empirically validate our method on visual MuJoCo continuous-control tasks, where final performance of several recent bisimulation-based RL algorithms is substantially improved when equipped with the distance we propose.

Related papers

• Manifold-Matching Autoencoders [5.232102034641475]
  We study a simple unsupervised regularization scheme for autoencoders called Manifold-Matching (MMAE)<n>We align the pairwise distances in the latent space to those of the input data space by minimizing mean squared error.<n>We find that this regularization outperforms similar methods on metrics based on preservation of nearest-neighbor distances and persistent homology-based measures.
  arXiv  Detail & Related papers  (2026-03-17T14:25:42Z)
• Deterministic Differentiable Structured Pruning for Large Language Models [37.33389749907146]
  Structured pruning reduces LLM inference cost by removing low-importance architectural components.<n>We propose Deterministic Differentiable Pruning (DDP), a mask-only optimization method.<n>Compared with prior approaches, DDP offers greater expressiveness, reduced train--test mismatch, and faster convergence.
  arXiv  Detail & Related papers  (2026-03-09T07:59:17Z)
• Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations [72.24831946301613]
  Approaches for goal-conditioned reinforcement learning (GCRL) often use learned state representations to extract goal-reaching policies.<n>We propose an approach that unifies these two frameworks, using the structure of a quasimetric representation space (triangle inequality) with the right additional constraints to learn successor representations that enable optimal goal-reaching.<n>Our approach is able to exploit a **quasimetric** distance parameterization to learn **optimal** goal-reaching distances, even with **suboptimal** data and in **stochastic** environments.
  arXiv  Detail & Related papers  (2025-09-24T18:45:32Z)
• APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction [16.82777427285544]
  Training deep learning models for point cloud prediction tasks depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets.<n>We propose Adaptive Probabilistic Matching Loss (APML), a fully differentiable approximation of one-to-one matching.<n>We analytically compute the temperature to guarantee a minimum probability, eliminating manual tuning.
  arXiv  Detail & Related papers  (2025-09-09T19:31:06Z)
• GeoMM: On Geodesic Perspective for Multi-modal Learning [55.41612200877861]
  This paper introduces geodesic distance as a novel distance metric in multi-modal learning for the first time.<n>Our approach incorporates a comprehensive series of strategies to adapt geodesic distance for the current multimodal learning.
  arXiv  Detail & Related papers  (2025-05-16T13:12:41Z)
• Improving Video Retrieval by Adaptive Margin [18.326296132847332]
  The dominant paradigm for video retrieval learns video-text representations by pushing the distance between the similarity of positive pairs and that of negative pairs apart from a fixed margin. Negative pairs used for training are sampled randomly, which indicates that the semantics between negative pairs may be related or even equivalent. We propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue.
  arXiv  Detail & Related papers  (2023-03-09T08:07:38Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)
• Boosting Continuous Sign Language Recognition via Cross Modality Augmentation [135.30357113518127]
  Continuous sign language recognition deals with unaligned video-text pair. We propose a novel architecture with cross modality augmentation. The proposed framework can be easily extended to other existing CTC based continuous SLR architectures.
  arXiv  Detail & Related papers  (2020-10-11T15:07:50Z)
• Towards Certified Robustness of Distance Metric Learning [53.96113074344632]
  We advocate imposing an adversarial margin in the input space so as to improve the generalization and robustness of metric learning algorithms. We show that the enlarged margin is beneficial to the generalization ability by using the theoretical technique of algorithmic robustness.
  arXiv  Detail & Related papers  (2020-06-10T16:51:53Z)

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.