Multi-Agent Reinforcement Learning for Base Station Placement in TDOA-Based Localization

Accurate localization of devices is a key capability for emerging 5G and 6G networks and depends on effective base station (BS) placement. Conventional geometry-based approaches such as Geometric Dilution of Precision (GDOP) ignore realistic propagation effects such as Non-Line of Sight (NLOS) shadowing and multipath-induced Time of Arrival (TOA) bias caused by buildings. This paper proposes a ray-tracing-assisted Multi-Agent Reinforcement Learning (MARL) framework for environment-aware BS placement in Time Difference of Arrival (TDOA) localization systems. Proximal Policy Optimization (PPO) agents are trained on Channel Impulse Responses (CIRs) generated from a detailed 3D model of a university campus. Each agent cooperatively places one BS while optimizing a shared reward that combines localization accuracy and coverage. The approach is evaluated on five campus segments with varying propagation characteristics. Results show that the learned policy achieves localization accuracy comparable to conventional GDOP-based placement, lowering the average localization Mean Absolute Error (MAE) by about 3 % relative to the stronger (mean-optimized) geometric baseline. The behavior is segment-dependent, with a clear improvement on individual segments (up to about 14 %) and comparable or slightly higher error on the others. These findings indicate that incorporating site-specific propagation data into the placement process can match and selectively improve upon purely geometric strategies, motivating further work toward consistent gains.