CT-PPO and JC-PPO Experimental Artifacts for Multi-Tenant ISAC Sensing-Session Consolidation

Experimental artifacts supporting the manuscript “Sense Once, Serve Many: Common-Trace Factorized Constrained PPO for Online Sensing-Session Consolidation in Multi-Tenant ISAC Networks.” This deposit contains ten final learned-policy experiment bundles: five Common-Trace PPO (CT-PPO) runs and five matched Joint-Credit PPO (JC-PPO) runs for training seeds 0–4. The bundles contain the run metadata and detailed artifacts associated with the final training and evaluation runs. Each learned-policy run uses a budget of 1,000,000 physical interaction slots. The deposit also contains report_heuristic.json, which records the evaluation results for the four heuristic baselines and Random Valid used in the manuscript. Together, these artifacts support the multi-seed CT-PPO/JC-PPO evaluation, matched comparisons, regime-wise analyses, consolidation metrics, and heuristic baseline comparisons reported in the manuscript. The associated implementation and training/evaluation scripts are available in the linked public software repository.