OCNR: Stabilizing Self-Play by Mitigating Iteration-Collapse With One-Class Novelty Rewards
Jul 6, 2026·
,,,·
0 min read
Seungyoo Lee
Giung Nam
Hyungi Lee†
Juho Lee†
Type
Publication
In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), PMLR 306
Accepted
April 30, 2026