Improving environment novelty quantification for effective unsupervised environment design

• Main Authors: TEOH, Jayden, LI, Wenjun, VARAKANTHAM, Pradeep
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Unsupervised environment design; Regret-driven metric; Environment novelty; Databases and Information Systems; Educational Assessment, Evaluation, and Research
• Online Access: https://ink.library.smu.edu.sg/sis_research/9921
• Institution: Singapore Management University

Unsupervised Environment Design (UED) formalizes the problem of autocurricula through interactive training between a teacher agent and a student agent. The teacher generates new training environments with high learning potential, curating an adaptive curriculum that strengthens the student’s ability...