A reputation-oriented reinforcement learning approach for agents in electronic marketplaces
Bibliographic record
Abstract
The problem of how to design personal, intelligent agents for e-commerce applications is a subject of increasing interest from both the academic and industrial research communities. In our research, we consider the agent environment as an open marketplace which is populated with economic agents (buyers and sellers), freely entering or leaving the market. The problem we are addressing is how best to model the electronic marketplace, and what kinds of learning strategies should be provided, in order to improve the performance of buyers and sellers in electronic exchanges. Our strategy is to introduce a reputation-oriented reinforcement learning algorithm for buyers and sellers. We take into account the fact that multiple sellers may offer the same good with different qualities. In our approach, buyers learn to maximize their expected value of goods and to avoid the risk of purchasing low quality goods by dynamically maintaining sets of reputable sellers. Sellers learn to maximize their expected profits by adjusting product prices and by optionally altering the quality of their goods. In our buying algorithm, a buyer b uses an expected value function f b , where f b (g, p,s) represents buyer b’s expected value of buying good g at price p from seller s. Buyer b maintains reputation ratings for sellers, and chooses among its set of reputable sellers S b
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".