Probe-Based Directional Credit Assignment

Read full text Summarise with VIRAT
Authors: Richard Vermillion
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We propose a framework for delayed credit assignment that sits between scalar eligibility traces and full gradient transport. The central idea is to attach a small probe dictionary to each perturbable module, instantiate a batch of nearby counterfactual trajectories by selecting probe directions across modules, and use delayed modulatory signals to reinforce or suppress the sampled directions. The framework is intended for settings in which full end-to-end gradients are unavailable, undesirable, biologically implausible, too expensive, or simply not the right abstraction. Its core objects are: (1) per-module probe dictionaries, (2) an assignment matrix defining which probe each module uses in each sampled trajectory, (3) directional eligibility traces that store sampled local directions over time, and (4) a scheduler that allocates limited perturbation budget across modules and trajectories. This note is a proposal rather than a validated empirical claim. Its purpose is to articulate the framework, position it relative to related ideas, and define a concrete experimental agenda.

Fields of Study & Subjects

Reinforcement Learning in Robotics Neural Networks and Applications Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
30 March 2026
Language
EN
Document type
Preprint