Metraipolis › archive › dc_cfcb80ecd235

Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist — arXiv:2611.01769

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01769
License (as archived): CC0-1.0
Archived: 2026-11-03T11:06:43.695Z
SHA-256 of the archived text: 6063b0419ec75dcf724b51cc03ae586cfd232b34ddf1dc6de4b06aa2877f4f87
Stable URL of this page: https://metraipolis.com/documento/dc_cfcb80ecd235

How to cite

Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist — arXiv:2611.01769 — arXiv (en), https://arxiv.org/abs/2611.01769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cfcb80ecd235 (Metraipolis archive dc_cfcb80ecd235, sha256 6063b0419ec75dcf724b51cc03ae586cfd232b34ddf1dc6de4b06aa2877f4f87)

BibTeX

@misc{dccfcb80ecd235,
  title = {Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist — arXiv:2611.01769},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01769},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cfcb80ecd235; sha256 6063b0419ec75dcf724b51cc03ae586cfd232b34ddf1dc6de4b06aa2877f4f87},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement-learning (RL) benchmarks built on microscopic traffic simulators such as SUMO are increasingly used to compare agent architectures for electric vehicle (EV) charging assignment. Unlike crashes, defects in the reward function, the environment's stochastic model, or the state encoding often fail silently: the simulation completes, produces plausible numbers, and the comparison is biased. We report five such defects, found by auditing a five-agent benchmark on OpenStreetMap road networks, stated generically: a shared random generator that desynchronises seed-paired comparisons, an ablation-specific reward clip applied unconditionally, a normalisation mismatch that zeroes a reward term, a per-timestep penalty that should fire once per event, and a state dimensionality documented but never wired into the network. We quantify three: a rejection counter inflated up to 125x across agents/cities, a reward term bounded at about $10^{-4}$ of its intended scale, and a 16.6%/16.3% greedy-action divergence from a state-encoding mismatch. Re-analysing a historical ablation, no A1-A2 effect survives family-wise correction; a 56-run campaign confirms the RNG defect's mechanism directly while showing its correction does not change that conclusion. We provide an eight-item checklist as a low-cost first-pass audit; in a later regeneration, three checks caught two new defects while three further process/artefact defects fell outside its boundary.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01769 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:59:46.047Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).