# ARiADNE: A Reinforcement learning approach using Attention-based Deep Networks for Exploration

arXiv: https://arxiv.org/abs/2301.11575 · HTML: https://mlsanity.com/paper/2301.11575/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2023.

## Built on by (most cited first, 18 of 18)

- [Deep Reinforcement Learning-based Large-scale Robot Exploration](https://mlsanity.com/paper/2403.10833/) (2024)
- [DARE: Diffusion Policy for Autonomous Robot Exploration](https://mlsanity.com/paper/2410.16687/) (2024)
- [Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning](https://mlsanity.com/paper/2402.04894/) (2024)
- [HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks](https://mlsanity.com/paper/2408.03768/) (2024)
- [Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games](https://mlsanity.com/paper/2511.00811/) (2025)
- [SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas](https://mlsanity.com/paper/2510.19766/) (2025)
- [Reinforcement Learning Driven Multi-Robot Exploration via Explicit Communication and Density-Based Frontier Search](https://mlsanity.com/paper/2412.20049/) (2024)
- [MapExRL: Human-Inspired Indoor Exploration with Predicted Environment Context and Reinforcement Learning](https://mlsanity.com/paper/2503.01548/) (2025)
- [CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration](https://mlsanity.com/paper/2503.14254/) (2025)
- [HEADER: Hierarchical Robot Exploration via Attention-Based Deep Reinforcement Learning with Expert-Guided Reward](https://mlsanity.com/paper/2510.15679/) (2025)
- [FARE: Fast-Slow Agentic Robotic Exploration](https://mlsanity.com/paper/2601.14681/) (2026)
- [OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown Environments](https://mlsanity.com/paper/2406.07294/) (2024)
- [Privileged Reinforcement and Communication Learning for Distributed, Bandwidth-limited Multi-robot Exploration](https://mlsanity.com/paper/2407.20203/) (2024)
- [A Graph-Based Reinforcement Learning Approach with Frontier Potential Based Reward for Safe Cluttered Environment Exploration](https://mlsanity.com/paper/2504.11907/) (2025)
- [GRATE: a Graph transformer-based deep Reinforcement learning Approach for Time-efficient autonomous robot Exploration](https://mlsanity.com/paper/2509.12863/) (2025)
- [Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention](https://mlsanity.com/paper/2511.15358/) (2025)
- [R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability](https://mlsanity.com/paper/2511.17367/) (2025)
- [VANDERER: Map-Free Exploration using Future-Aware and Visual-Curiosity-Guided Diffusion Policy](https://mlsanity.com/paper/2606.14879/) (2026)

## Abstract (arXiv)

In autonomous robot exploration tasks, a mobile robot needs to actively explore and map an unknown environment as fast as possible. Since the environment is being revealed during exploration, the robot needs to frequently re-plan its path online, as new information is acquired by onboard sensors and used to update its partial map. While state-of-the-art exploration planners are frontier- and sampling-based, encouraged by the recent development in deep reinforcement learning (DRL), we propose ARiADNE, an attention-based neural approach to obtain real-time, non-myopic path planning for autonomous exploration. ARiADNE is able to learn dependencies at multiple spatial scales between areas of the agent's partial map, and implicitly predict potential gains associated with exploring those areas. This allows the agent to sequence movement actions that balance the natural trade-off between exploitation/refinement of the map in known areas and exploration of new areas. We experimentally demonstrate that our method outperforms both learning and non-learning state-of-the-art baselines in terms of average trajectory length to complete exploration in hundreds of simplified 2D indoor scenarios. We further validate our approach in high-fidelity Robot Operating System (ROS) simulations, where we consider a real sensor model and a realistic low-level motion controller, toward deployment on real robots.