cs.LGNov 16, 2026

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

Authors: Shivin Mangal, Divyansh Chawla, Anshu Garg, Isshaan Singh

Organizations: Vellore Institute of Technology (VIT), Chennai, India · MBZUAI, Abu Dhabi, UAE

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.

Figures & tables

Explore similar work

CardsList
  1. An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback

    Sep 5, 2026Lichen Wang, Shijia Hua, Linjie LiuMean-Field MARLMulti-Agent Reinforcement Learning

  2. AirPlayground: Benchmarking Aerial Navigation across Diverse Reconstructed Environments

    Oct 21, 2026Rangya Zhang, Yujing Shang, Zhuoyuan Yu +5UAV NavigationRobot Navigation Benchmarks

  3. Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

    Jan 13, 2026Youwei Liu, Jian Wang, Hanlin Wang +2World Model-Based PlanningModel-Based Planning