paper-with-me

Papers

An Optimization Framework for Task Sequencing in Curriculum Learning

2019-01-31 · Francesco Foglino, Christiano Coletto Christakou, Matteo Leonetti

Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with the objective of reducing the time to reach a given performance level. We propose novel uses of curriculum learning, which arise from choosing different objective functions. Furthermore, we define a general optimization framework for task sequencing and evaluate the performance of popular metaheuristic search methods on several tasks. We show that curriculum learning can be successfully used to: improve the initial performance, take fewer suboptimal actions during exploration, and discover better policies.

📄 PDF Abstract BibTeX arXiv:1901.11478

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Curriculum Learning for Cumulative Return Maximization

2019-06-13 · Francesco Foglino, Christiano Coletto Christakou, Ricardo Luna Gutierrez, Matteo Leonetti

Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal explorat…

Combinatorial OptimizationReinforcement LearningTransfer Learning

A Memetic Walrus Algorithm with Expert-guided Strategy for Adaptive Curriculum Sequencing

2025-06-16 · Qionghao Huang, Lingnuo Lu, Xuemei Wu, Fan Jiang 외

Adaptive Curriculum Sequencing (ACS) is essential for personalized online learning, yet current approaches struggle to balance complex educational constraints and maintain optimization stability. This paper proposes a Me…

Computational Efficiency

Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing

2025-06-16 · Xiang Zhang, Jiaqi Wei, Zijie Qiu, Sheng Xu 외

Peptide sequencing-the process of identifying amino acid sequences from mass spectrometry data-is a fundamental task in proteomics. Non-Autoregressive Transformers (NATs) have proven highly effective for this task, outpe…

de novo peptide sequencing

Sequencing to Mitigate Catastrophic Forgetting in Continual Learning

2025-12-18 · Hesham G. Moussa, Aroosa Hameed, Arashmid Akhavain arxiv

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI syste…

Neural Architecture SearchContinual Learning

Self Paced Gaussian Contextual Reinforcement Learning

2026-03-24 · Mohsen Sahraei Ardakani, Rui Song arxiv

Curriculum learning improves reinforcement learning (RL) efficiency by sequencing tasks from simple to complex. However, many self-paced curriculum methods rely on computationally expensive inner-loop optimizations, limi…

Reinforcement Learning