MétaCan
Menu
Back to cohort
Record W3203207428 · doi:10.1007/s00521-021-06259-1

Policy invariant explicit shaping: an efficient alternative to reward shaping

2021· article· en· W3203207428 on OpenAlex

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

VenueNeural Computing and Applications · 2021
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsUniversity of Alberta
FundersNatural Sciences and Engineering Research Council of CanadaCanadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of CanadaUniversity of AlbertaAlberta Machine Intelligence InstituteCompute CanadaCanadian Institute for Advanced Research
KeywordsReinforcement learningAdvice (programming)Computer scienceInvariant (physics)Function (biology)Process (computing)Temporal difference learningArtificial intelligenceMathematics

Abstract

fetched live from OpenAlex

Abstract Reinforcement learning (RL) is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can take hours, days, or even years of training data. A major challenge of contemporary RL research is to discover how to learn with less data. Previous work has shown that domain information can be successfully used to shape the reward; by adding additional reward information, the agent can learn with much less data. Furthermore, if the reward is constructed from a potential function, the optimal policy is guaranteed to be unaltered. While such potential-based reward shaping (PBRS) holds promise, it is limited by the need for a well-defined potential function. Ideally, we would like to be able to take arbitrary advice from a human or other agent and improve performance without affecting the optimal policy. The recently introduced dynamic potential-based advice (DPBA) was proposed to tackle this challenge by predicting the potential function values as part of the learning process. However, this article demonstrates theoretically and empirically that, while DPBA can facilitate learning with good advice, it does in fact alter the optimal policy. We further show that when adding the correction term to “fix” DPBA it no longer shows effective shaping with good advice. We then present a simple method called policy invariant explicit shaping (PIES) and show theoretically and empirically that PIES can use arbitrary advice, speed-up learning, and leave the optimal policy unchanged.

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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.904
Threshold uncertainty score0.660

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
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 head0.061
GPT teacher head0.329
Teacher spread0.268 · 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