Curriculum learning improves compositionality of reinforcement learning agent across concept classes

• المؤلف الرئيسي: Lin, Zijun
• مؤلفون آخرون: Wen Bihan
• التنسيق: Final Year Project
• اللغة: English
• منشور في: Nanyang Technological University 2024
• الموضوعات: Computer and Information Science; Reinforcement learning
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/176294

The compositional structure afforded by language allows humans to decompose complex phrases and map them to novel visual concepts, demonstrating flexible intelligence. Although there have been several algorithms that can demonstrate compositionality, they do not give us insights on how humans learn...