Devs Model Construction As A Reinforcement Learning Problem
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Simulators are crucial components in many software-intensive systems, such as cyber-physical systems and digital twins. The inherent complexity of such systems renders the manual construction of simulators an error-prone and costly endeavor, and automation techniques are much sought after. However, current automation techniques are typically tailored to a particular system and cannot be easily transposed to other settings. In this paper, we propose an approach for the automated construction of simulators that can overcome this limitation, based on the inference of Discrete Event System Specifications (DEVS) models by reinforcement learning. Reinforcement learning allows inferring knowledge on the construction process of the simulator, instead of inferring the simulator itself. This, in turn, fosters reuse across different systems. DEVS further improves the reusability of this knowledge, as the vast majority of simulation formalisms can be efficiently translated to DEVS. We demonstrate the performance and generalizability of our approach on an illustrative example implemented in Python and Tensorforce.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 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 it