---
license: apache-2.0
language:
- en
tags:
- reinforcement-learning
- embodied-ai
- 3d-exploration
- habitat
- gaussian-splatting
- vision-transformer
- ppo
pipeline_tag: reinforcement-learning
---

# Remember to be Curious — Pretrained Checkpoints

Pretrained checkpoints for:

> **Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration**  
> Lily Goli, Justin Kerr, Daniele Reda, Alec Jacobson, Andrea Tagliasacchi, Angjoo Kanazawa  
> *University of Toronto · UC Berkeley · Wayve · Vector Institute · Simon Fraser University*  
> [[Project page]](https://recuriosity.github.io) · [[Code]](https://github.com/recuriosity/recuriosity)

## Model description

A reinforcement learning agent that learns to explore 3D indoor scenes using only an RGB camera. The policy uses a DINO ViT-B/8 visual encoder with a sliding-window transformer backbone (KV-cached), trained with PPO. Intrinsic reward is derived from real-time Gaussian Splatting (GSplat) reconstruction quality.

## Checkpoints

| File | Description |
|------|-------------|
| `explorer.pt` | Main exploration policy, trained on HM3D |
| `apple_finetuned.pt` | Apple-picking fine-tune (from `explorer.pt`) |
| `image_goal_finetuned.pt` | Image-goal navigation fine-tune (from `explorer.pt`) |

## Usage

See the [code repository](https://github.com/recuriosity/recuriosity) for full installation and evaluation instructions.

## Training data

Trained on [Habitat-Matterport 3D (HM3D)](https://aihabitat.org/datasets/hm3d/) scenes using the [Habitat-Sim](https://github.com/facebookresearch/habitat-sim) simulator.