# Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations

arXiv: https://arxiv.org/abs/2402.03138 · HTML: https://mlsanity.com/paper/2402.03138/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [First return, then explore](https://mlsanity.com/paper/2004.12919/) (2020)
- [Count-Based Exploration with Neural Density Models](https://mlsanity.com/paper/1703.01310/) (2017)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments](https://mlsanity.com/paper/2002.12292/) (2020)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [Exploration via Elliptical Episodic Bonuses](https://mlsanity.com/paper/2210.05805/) (2022)
- [Interesting Object, Curious Agent: Learning Task-Agnostic Exploration](https://mlsanity.com/paper/2111.13119/) (2021)
- [A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs](https://mlsanity.com/paper/2306.03236/) (2023)
- [Unlocking the Power of Representations in Long-term Novelty-based Exploration](https://mlsanity.com/paper/2305.01521/) (2023)
- [Clustered Reinforcement Learning](https://mlsanity.com/paper/1906.02457/) (2019)
- [Cyclophobic Reinforcement Learning](https://mlsanity.com/paper/2308.15911/) (2023)

## Built on by (most cited first, 3 of 3)

- [I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames](https://mlsanity.com/paper/2412.01296/) (2024)
- [K*-Means: A Parameter-free Clustering Algorithm](https://mlsanity.com/paper/2505.11904/) (2025)
- [Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations](https://mlsanity.com/paper/2503.09867/) (2025)

## Abstract (arXiv)

In this paper we adopt a representation-centric perspective on exploration in reinforcement learning, viewing exploration fundamentally as a density estimation problem. We investigate the effectiveness of clustering representations for exploration in 3-D environments, based on the observation that the importance of pixel changes between transitions is less pronounced in 3-D environments compared to 2-D environments, where pixel changes between transitions are typically distinct and significant. We propose a method that performs episodic and global clustering on random representations and on pre-trained DINO representations to count states, i.e, estimate pseudo-counts. Surprisingly, even random features can be clustered effectively to count states in 3-D environments, however when these become visually more complex, pre-trained DINO representations are more effective thanks to the pre-trained inductive biases in the representations. Overall, this presents a pathway for integrating pre-trained biases into exploration. We evaluate our approach on the VizDoom and Habitat environments, demonstrating that our method surpasses other well-known exploration methods in these settings.