Bibliographic record
Abstract
The use of learning, in particular reinforcement learning, has been explored in the context of policy-driven autonomic management as a means of aiding decision making. In this context, the autonomic manager “learns” a model about what actions to take, for example, in certain situations. However, when the set of policies changes, the model is typically discarded or, if used, may yield misleading information. In contrast, this paper presents an approach for “re-using” past knowledge - by transforming a model learned from the use of one set of active policies to a new model when those policies change. This means that some of the “learned” knowledge can be utilized within the new environment. This is possible because our approach to modeling learning and adaptation is dependent only on the structure of the policies. Consequently, changes to policies can be mapped onto transformations specific to the model derived from the use of those policies. In this paper, we describe the model construction and policy modifications and elaborate, with a detailed case study, on how such changes could alter the currently learned model. Our analysis of the different kinds of policy modifications also suggest that, in most cases, most of the learned model can still be reused. This can significantly accelerate the learning process, essentially improving the overall quality of service, as the results presented in this paper demonstrate.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".