# Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning

arXiv: https://arxiv.org/abs/2302.04125 · HTML: https://mlsanity.com/paper/2302.04125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 7 of 7)

- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Self-Supervised Exploration via Disagreement](https://mlsanity.com/paper/1906.04161/) (2019)
- [A survey on intrinsic motivation in reinforcement learning](https://mlsanity.com/paper/1908.06976/) (2019)
- [rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch](https://mlsanity.com/paper/1909.01500/) (2019)
- [A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications](https://mlsanity.com/paper/1905.11437/) (2019)

## Built on by (most cited first, 1 of 1)

- [Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs](https://mlsanity.com/paper/2309.15395/) (2023)

## Abstract (arXiv)

We introduce an exploration bonus for deep reinforcement learning methods calculated using self-organising feature maps. Our method uses adaptive resonance theory (ART) providing online, unsupervised clustering to quantify the novelty of a state. This heuristic is used to add an intrinsic reward to the extrinsic reward signal for then to optimize the agent to maximize the sum of these two rewards. We find that this method was able to play the game Ordeal at a human level after a comparable number of training epochs to ICM arXiv:1705.05464. Agents augmented with RND arXiv:1810.12894 were unable to achieve the same level of performance in our space of hyperparameters.