An adaptive extremum-seeking control approach to reinforcement learning
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
In this study, we consider a set-based adaptive reinforcement learning framework for the design of optimal control systems for a class of nonlinear systems with unknown dynamics. Assuming that the system has access to the measurement of a set of basis functions, the proposed set-based approach is shown to guarantee convergence to a neighbourhood of the optimal value function. In contrast to existing nonlinear reinforcement learning technique, the proposed approach does not require a parametrization of the unknown dynamics. The dynamics are estimated using a nonparametric learning techniques inspired by extremum seeking control techniques. In particular, a timescale transformation approach is proposed to estimate the drift and control component of each basis functions. The stability of the proposed control system is guaranteed if the trajectories of the system meet a persistency of excitation condition. A simulation study is conducted to demonstrate the effectiveness of the proposed approach.
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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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