Comparison of Two Reward Functions for a Multi-Stack Hybrid Trike Motor
Bibliographic record
Abstract
In a multi-stack fuel cell (FC) hybrid electric vehicle (HEV), the power sources (battery and FC) have different energetic characteristics. Hence, efficient power distribution for such a multi-source system is a critical issue. Reinforcement learning (RL) has been recently introduced as a potential tool for energy management strategy (EMS) design in FC-HEVs. However, the desirable performance of RL is concerned with the definition of a suitable performance criterion, known as reward function, based on which the agents out to take actions in an environment. Hence, the definition of a suitable reward function is of great importance. Maximizing the performance and lifespan of the energy sources whilst minimizing the fuel consumption are typical examples of the operational criteria in a FC-HEV. These conflicting criteria normally try to quantify the trade-offs in satisfying different objectives or to find a single solution that satisfies the subjective preferences. This study aims at comparing the performance of an RL-based EMS in a multi-stack FC-HEV, composed of two FCs and a battery pack, using two different reward functions. The utilized reward functions are based on hydrogen and degradation minimization, and efficiency enhancement. The obtained results under a standard driving cycle show that applying the reward function for efficiency enhancement leads to fairly similar results as the multi-objective one.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".