MétaCan
Menu
Back to cohort
Record W3128954025 · doi:10.1609/aaai.v35i9.16964

Variance Penalized On-Policy and Off-Policy Actor-Critic

2021· article· en· W3128954025 on OpenAlexaff
Arushi Jain, Gandharv Patil, Ayush Jain, Khimya Khetarpal, Doina Precup

Bibliographic record

VenueProceedings of the AAAI Conference on Artificial Intelligence · 2021
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsMila - Quebec Artificial Intelligence InstituteMcGill University
Fundersnot available
KeywordsVariance (accounting)Convergence (economics)Computer scienceReinforcement learningEstimatorMoment (physics)Markov decision processExpected returnMathematical optimizationMinimum-variance unbiased estimatorVariance risk premiumEconometricsMathematicsArtificial intelligenceMarkov processStatisticsEconomics

Abstract

fetched live from OpenAlex

Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this paper, we propose on-policy and off-policy actor-critic algorithms that optimize a performance criterion involving both mean and variance in the return. Previous work uses the second moment of return to estimate the variance indirectly. Instead, we use a much simpler recently proposed direct variance estimator which updates the estimates incrementally using temporal difference methods. Using the variance-penalized criterion, we guarantee the convergence of our algorithm to locally optimal policies for finite state action Markov decision processes. We demonstrate the utility of our algorithm in tabular and continuous MuJoCo domains. Our approach not only performs on par with actor-critic and prior variance-penalization baselines in terms of expected return, but also generates trajectories which have lower variance in the return.

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.

How this classification was reachedexpand

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)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.874
Threshold uncertainty score0.961

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0020.001
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 head0.063
GPT teacher head0.321
Teacher spread0.258 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the AAAI Conference on Artificial IntelligenceSame topicReinforcement Learning in RoboticsFrench-language works237,207