# Self-Organizing Maps for Storage and Transfer of Knowledge in Reinforcement Learning

arXiv: https://arxiv.org/abs/1811.08318 · HTML: https://mlsanity.com/paper/1811.08318/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Assemble Foundation Models for Automatic Code Summarization](https://mlsanity.com/paper/2201.05222/) (2022)
- [Deep Network Approximation in Terms of Intrinsic Parameters](https://mlsanity.com/paper/2111.07964/) (2021)
- [LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying](https://mlsanity.com/paper/2308.13542/) (2023)
- [A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning](https://mlsanity.com/paper/2305.01507/) (2023)
- [An Adaptive Resonance Theory-based Topological Clustering Algorithm with a Self-Adjusting Vigilance Parameter](https://mlsanity.com/paper/2511.17983/) (2025)
- [The tree reconstruction game: phylogenetic reconstruction using reinforcement learning](https://mlsanity.com/paper/2303.06695/) (2023)
- [Deep-learning recognition and tracking of individual nanotubes in low-contrast microscopy videos](https://mlsanity.com/paper/2410.13594/) (2024)
- [A Domain-Adapted Lightweight Ensemble for Resource-Efficient Few-Shot Plant Disease Classification](https://mlsanity.com/paper/2512.13428/) (2025)

## Abstract (arXiv)

The idea of reusing or transferring information from previously learned tasks (source tasks) for the learning of new tasks (target tasks) has the potential to significantly improve the sample efficiency of a reinforcement learning agent. In this work, we describe a novel approach for reusing previously acquired knowledge by using it to guide the exploration of an agent while it learns new tasks. In order to do so, we employ a variant of the growing self-organizing map algorithm, which is trained using a measure of similarity that is defined directly in the space of the vectorized representations of the value functions. In addition to enabling transfer across tasks, the resulting map is simultaneously used to enable the efficient storage of previously acquired task knowledge in an adaptive and scalable manner. We empirically validate our approach in a simulated navigation environment, and also demonstrate its utility through simple experiments using a mobile micro-robotics platform. In addition, we demonstrate the scalability of this approach, and analytically examine its relation to the proposed network growth mechanism. Further, we briefly discuss some of the possible improvements and extensions to this approach, as well as its relevance to real world scenarios in the context of continual learning.