Neuromodulation + Eligibility Traces (Three-Factor Learning)

Community

Three-factor learning guided by neuromodulation.

Authorsovr610
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Enables online, neuromodulation-driven gating of eligibility traces for three-factor learning, bridging local synaptic activity with delayed modulatory signals to drive plasticity.

Core Features & Use Cases

  • Supports accumulating, replacing, and Dutch trace variants with rate-based and STDP kernels, enabling flexible online learning in biologically inspired architectures.
  • Provides end-to-end config via EligibilityConfig, NeuromodConfig, ThreeFactorConfig, and PlasticityFullConfig for online, hybrid, and auxiliary_loss modes.
  • Real-world use: accelerate reward-guided adaptation in cognitive agents by gating weight updates with DA/ACh/NE/5-HT signals.

Quick Start

Initialize the Neuromodulation + Eligibility Traces skill and execute a minimal online three-factor update using a reward signal.

Dependency Matrix

Required Modules

torch

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Neuromodulation + Eligibility Traces (Three-Factor Learning)
Download link: https://github.com/sovr610/refffiy/archive/main.zip#neuromodulation-eligibility-traces-three-factor-learning

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.