Rich Learning: Topological Graph Memory for Lifelong Reinforcement Learning
Abstract
Rich Learning is a reinforcement learning paradigm that addresses catastrophic forgetting through topological graph memory. Knowledge is stored as navigable landmarks and transitions in a graph database, enabling zero-forgetting continual learning across sequential tasks.
Fields of Study & Subjects
Reinforcement Learning in Robotics
Domain Adaptation and Few-Shot Learning
AI-based Problem Solving and Planning
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 9 February 2026