cs.LGNov 1, 2026

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

Authors: Nour-Eddine Moumni, Rachid Alaoui, Driss Kiouach

Organizations: Laboratory of Research in Computer Science and Telecommunications (LRIT), Mohammed V University, Rabat, Morocco · Higher School of Technology of Salé, Mohammed V University, Rabat, Morocco · Laboratory of Probability, Statistics and Intelligent Systems (LPAIS), Sidi Mohamed Ben Abdellah University, Fez, Morocco

Abstract

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 10−410^{-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.

Explore similar work

CardsList
  1. Cooperative EV Charging Assignment Using Multi-Agent Reinforcement Learning: A Comparison of QMIX and Independent Q-Learning Under Urban Traffic Uncertainty

    Oct 27, 2026Nour-Eddine Moumni, Rachid Alaoui, Driss KiouachElectric Vehicle ChargingCooperative MARL

  2. SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking

    Mar 3, 2026Mertcan Daysalilar, Fuat Uyguroglu, Gabriel Nicolosi +1Synthetic Benchmark GenerationVehicle Routing

  3. A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch

    Apr 28, 2026An Nguyen, Hoang Nguyen, Phuong Le +3Electric Vehicle ChargingConstrained RL