Agnostic KWIK learning and efficient approximate 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
A popular approach in reinforcement learning is to use a model-based algorithm, i.e., an algorithm that utilizes a model learner to learn an approximate model to the environment. It has been shown that such a model-based learner is ecient if the model learner is ecient in the so-called \knows what it knows (KWIK) framework. A major limitation of the standard KWIK framework is that, by its very denition, it covers only the case when the (model) learner can represent the actual environment with no errors. In this paper, we study the agnostic KWIK learning model, where we relax this assumption by allowing nonzero approximation errors. We show that with the new denition an ecient model learner still leads to an ecient reinforcement learning algorithm. At the same time, though, we nd that learning within the new framework can be substantially slower as compared to the standard framework, even in the case of simple learning problems.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it