MétaCan
Menu
Back to cohort

Non-divergent Imitation for Verification of Complex Learned Controllers

2021· article· en· W3200761006 on OpenAlex
Vahdat Abdelzad, Jaeyoung Lee, Sean Sedwards, Soheil Soltani, Krzysztof Czarnecki

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsOracleComputer scienceMaximizationContext (archaeology)DistillationMetric (unit)FidelityArtificial intelligenceMachine learningMathematical optimizationMathematicsEngineering

Abstract

fetched live from OpenAlex

We consider the problem of verifying complex learned controllers using distillation. In contrast to previous work, we require that the distilled model maintains behavioural fidelity with an oracle, defining the notion of non-divergent path length (NPL) as a metric. We demonstrate that current distillation approaches with proven accuracy bounds do not have high expected NPL and can be out-performed by naive behavioural cloning. We thus propose a distillation algorithm that typically gives greater expected NPL, improved sample efficiency, and more compact models. We prove properties of NPL maximization and demonstrate the performance of our algorithm on deep Q-network controllers for three standard learning environments that have been used in this context: Pong, CartPole and MountainCar.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.777
Threshold uncertainty score0.268

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.055
GPT teacher head0.315
Teacher spread0.260 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it