SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1801–1810 of 3569 papers

TitleStatusHype
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision—0
Model agnostic meta-learning on trees—0
Model-Agnostic Meta-Learning using Runge-Kutta Methods—0
Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective—0
First-order ANIL provably learns representations despite overparametrization—0
Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators—0
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning—0
Model Based Meta Learning of Critics for Policy Gradients—0
Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning—0
ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control—0
Show:102550
← PrevPage 181 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified