A curriculum sampling questions with high variance in success rate improves reinforcement learning performance for LLM reasoning tasks.
Automated Curriculum Learning for Neural Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the amount that the network learns from each data sample is provided as a reward signal to a nonstationary multi-armed bandit algorithm, which then determines a stochastic syllabus. We consider a range of signals derived from two distinct indicators of learning progress: rate of increase in prediction accuracy, and rate of increase in network complexity. Experimental results for LSTM networks on three curricula demonstrate that our approach can significantly accelerate learning, in some cases halving the time required to attain a satisfactory performance level.
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
The paper advocates incorporating biological learning principles such as developmental learning, curriculum learning, transfer learning, and intrinsic motivation into continual learning models for autonomous agents and robots.
citing papers explorer
-
Learning to Reason at the Frontier of Learnability
A curriculum sampling questions with high variance in success rate improves reinforcement learning performance for LLM reasoning tasks.
-
Rethinking Continual Learning for Autonomous Agents and Robots
The paper advocates incorporating biological learning principles such as developmental learning, curriculum learning, transfer learning, and intrinsic motivation into continual learning models for autonomous agents and robots.