# Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World Model

arXiv: https://arxiv.org/abs/2603.18853 · HTML: https://mlsanity.com/paper/2603.18853/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction](https://mlsanity.com/paper/2408.08593/) (2024)
- [Wireless Communications with Unmanned Aerial Vehicles: Opportunities and Challenges](https://mlsanity.com/paper/1602.03602/) (2016)
- [Toward Immersive Communications in 6G](https://mlsanity.com/paper/2303.05283/) (2023)
- [Inexact Block Coordinate Descent Algorithms for Nonsmooth Nonconvex Optimization](https://mlsanity.com/paper/1905.04211/) (2019)
- [Toward Enhanced Reinforcement Learning-Based Resource Management via Digital Twin: Opportunities, Applications, and Challenges](https://mlsanity.com/paper/2406.07857/) (2024)
- [Challenges and Opportunities of Future Rural Wireless Communications](https://mlsanity.com/paper/2108.05405/) (2021)

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

- [ClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physics](https://mlsanity.com/paper/2610.17419/) (2026)

## Abstract (arXiv)

Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things networks, but their trajectories couple nonlinear wireless rates with long-horizon service progress. This paper views the evolution of AAV kinematics, channel state, and user backlog as a structured differentiable world model and develops Learn for Variation (L4V) to exploit that model efficiently. L4V replaces a discontinuous completion-time objective with a cumulative-backlog surrogate, unrolls the mission dynamics, and propagates pathwise sensitivities to a neural policy through the discrete adjoint recursion. The resulting derivative is exact conditional on a fixed exogenous-noise realization; stochastic expected-objective optimization still requires sampling. We show that the structured adjoint grows at most polynomially with the horizon and establish a stationary-point rate for fixed-step full-gradient descent under standard smoothness assumptions. The framework also learns shared OFDMA allocation under reparameterized shadowing and Rician fading, while distributional pretraining amortizes model-based optimization into forward-only deployment on unseen layouts. Paired stress tests cover channel-generator mismatch, noisy partial observations, a fixed-resource two-AAV extension, and a circular no-fly region. Code and configurations are available at https://github.com/UNIC-Lab/L4V-AAV. Against genetic-algorithm, DQN, A2C, DDPG, and differentiable model-predictive-control implementations, L4V reduces mission time by up to 65%, executes a default mission in 53 ms, and completes all 60 frozen-policy tests after pretraining on 1,600 layouts.