REVIEW 2 cited by
ES-MAML: Simple Hessian-Free Meta Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are based on policy gradients, and incur significant difficulties when attempting to estimate second derivatives using backpropagation on stochastic policies. We show how ES can be applied to MAML to obtain an algorithm which avoids the problem of estimating second derivatives, and is also conceptually simple and easy to implement. Moreover, ES-MAML can handle new types of nonsmooth adaptation operators, and other techniques for improving performance and estimation of ES methods become applicable. We show empirically that ES-MAML is competitive with existing methods and often yields better adaptation with fewer queries.
Forward citations
Cited by 2 Pith papers
-
Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning
A derivative-free coreset task-selection algorithm for MAML-RL trains on a small weighted task subset and provably reduces sample complexity by O(1/epsilon), provided the task-selection bias is small.
-
Adaptive Policy Backbone via Shared Network
Adapting only linear layers before and after a frozen shared backbone is enough to transfer to out-of-distribution continuous-control tasks, with a theoretical argument and MuJoCo experiments.
Discussion (0). Continue with ORCID to comment.