Discrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs

arXiv:2610.05071 · cs.LG, cs.AI · Submitted 2026-10-04 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-04

Updated: 2026-10-04

Code: https://github.com/dariorancati/discrete-gradient-flow

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Stochastic Dynamics — 1× in this paper · explained in 3 episodes

Sources

• DICE: Discrete inverse continuity equation for learning population dynamics
• Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphs
• Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots
• Gradient-flow SDEs have unique transient population dynamics
• Geometric calculations on probability manifolds from reciprocal relations in Master equations
• Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
• Optimal Transport for Machine Learners
• Accelerated Markov Chain Monte Carlo Algorithms on Discrete States

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks