# World-Grounded Reinforcement Learning for Pollution-Aware Bird Movement Modeling Using a Multi-Instance DQN Framework

> Source: <https://arxiv.org/abs/2611.21895>
> Published: 2026-11-18 05:00:00+00:00

**Key takeaway:** Replacing repeated real-time API queries with a precomputed AQI lookup matrix let the multi-instance DQN train and run faster, and the DQN beat Monte Carlo, Q-Learning, and Value Iteration baselines on stability and cumulative performance under pollution constraints.

arXiv:2611.21895v1 Announce Type: new 
Abstract: Birds are modeled as environmentally sensitive agents whose movement reflects real-world air quality conditions, where AQI serves as a measurable world feedback signal representing pollution-driven consequences. Instead of relying on human preference or synthetic rewards, the system uses environmental outcomes as the primary training signal, enabling policy learning grounded in ecological impact. We propose a multi-instance reinforcement learning simulation in which agents navigate a 2D grid representation of India integrated with a precomputed AQI matrix and geographic state boundaries. The framework combines bird call metadata from the Xeno-canto dataset, spatial discretization, and real environmental data to learn adaptive navigation strategies under pollution constraints. To ensure scalability and efficiency, repeated real-time API queries are replaced by a structured AQI mapping that enables fast lookup during training and execution. Multiple baselines, including Monte Carlo, Q-Learning, and Value Iteration, are evaluated for comparison. Deep Q-Network demonstrates stronger stability, adaptability, and cumulative performance across varying environmental conditions, establishing a scalable foundation for world-feedback driven ecological decision modeling.
