RLTE: A Reinforcement Learning Based Trust Establishment Model
Bibliographic record
Abstract
Trust is a complex, multifaceted concept that includes more than just evaluating others' honesty. Many trust evaluation models have been proposed and implemented in different areas, most of them focused on creating algorithms for trusters to model the honesty of trustees in order to make effective decisions about which trustees to select, where a rational truster is supposed to interact with the trustworthy ones. If interactions are based on trust, trustworthy trustees will have a greater impact on the results of interactions' results. Consequently, building a high trust may be an advantage for rational trustees. This work describes a Reinforcement Learning based Trust Establishment model (RLTE) that goes beyond trust evaluation to outline actions to direct trustees (instead of trusters). RLTE uses the retention of trusters and reinforcement learning to model trustors' behaviors. A trustee uses reinforcement learning to adjust the utility gain it provides when interacting with each truster. The trustee depends on the average number of transactions carried out by that truster, relative to the mean number of transactions performed by all trusters interacting with this trustee. The trustee accelerates or decelerates the adjustment of the utility gain based on the increase or decrease of the average retention rate of all trusters in the society, respectively. The proposed model does not depend on direct feedback, nor does it depend on the current reputation of trustees in the environment. Simulation results indicate that trustees empowered with the proposed model can be selected more by trusters.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".