On the Learning and Learnability of Quasimetrics
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:IP24ONFCrecord.jsonopen to challenge →
read the original abstract
Our world is full of asymmetries. Gravity and wind can make reaching a place easier than coming back. Social artifacts such as genealogy charts and citation graphs are inherently directed. In reinforcement learning and control, optimal goal-reaching strategies are rarely reversible (symmetrical). Distance functions supported on these asymmetrical structures are called quasimetrics. Despite their common appearance, little research has been done on the learning of quasimetrics. Our theoretical analysis reveals that a common class of learning algorithms, including unconstrained multilayer perceptrons (MLPs), provably fails to learn a quasimetric consistent with training data. In contrast, our proposed Poisson Quasimetric Embedding (PQE) is the first quasimetric learning formulation that both is learnable with gradient-based optimization and enjoys strong performance guarantees. Experiments on random graphs, social graphs, and offline Q-learning demonstrate its effectiveness over many common baselines.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.