# Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training

arXiv: https://arxiv.org/abs/2604.26833 · HTML: https://mlsanity.com/paper/2604.26833/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 15 of 15)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [You Only Live Once: Single-Life Reinforcement Learning](https://mlsanity.com/paper/2210.08863/) (2022)
- [Large Batch Simulation for Deep Reinforcement Learning](https://mlsanity.com/paper/2103.07013/) (2021)
- [Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation](https://mlsanity.com/paper/2601.07821/) (2026)
- [UAV Path Planning Employing MPC- Reinforcement Learning Method Considering Collision Avoidance](https://mlsanity.com/paper/2302.10669/) (2023)
- [Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models](https://mlsanity.com/paper/2512.11908/) (2025)
- [Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay](https://mlsanity.com/paper/2402.18487/) (2024)
- [PPO-based Dynamic Control of Uncertain Floating Platforms in the Zero-G Environment](https://mlsanity.com/paper/2407.03224/) (2024)
- [A Survey on DRL based UAV Communications and Networking: DRL Fundamentals, Applications and Implementations](https://mlsanity.com/paper/2502.12875/) (2025)
- [Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications](https://mlsanity.com/paper/2308.10393/) (2023)
- [Safe Hierarchical Reinforcement Learning for CubeSat Task Scheduling Based on Energy Consumption](https://mlsanity.com/paper/2309.12004/) (2023)
- [Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement Learning](https://mlsanity.com/paper/2502.05996/) (2025)
- [MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigation](https://mlsanity.com/paper/2509.21045/) (2025)

## Abstract (arXiv)

This paper presents a hierarchical decision-making framework for unmanned aerial vehicle (UAV) missions motivated by search-and-rescue (SAR) scenarios under limited simulation training. The framework combines a fixed rule-based high-level advisor with an online goal-conditioned low-level reinforcement learning (RL) controller. To stress-test early adaptation, we also consider a strict no-pretraining deployment regime. The high-level advisor is defined offline from a structured task specification and compiled into deterministic rules. It provides interpretable mission- and safety-aware guidance through recommended actions, avoided actions, and regime-dependent arbitration weights. The low-level controller learns online from task-defined dense rewards and reuses experience through a mode-aware prioritized replay mechanism augmented with rule-derived metadata. We evaluate the framework on two tasks: battery-aware multi-goal delivery and moving-target delivery in obstacle-rich environments. Across both tasks, the proposed method improves early safety and sample efficiency primarily by reducing collision terminations, while preserving the ability to adapt online to scenario-specific dynamics.