Recent work on designing an appropriate distribution of environments has shown promise for training effective generally capable agents. Its success is partly because of a form of adaptive curriculum learning that generates environment instances (or levels) at the frontier of the agent's capabilities. However, such an environment design framework often struggles to find effective levels in challenging design spaces and requires costly interactions with the environment. In this paper, we aim to introduce diversity in the Unsupervised Environment Design (UED) framework. Specifically, we propose a task-agnostic method to identify observed/hidden states that are representative of a given level. The outcome of this method is then utilized to characterize the diversity between two levels, which as we show can be crucial to effective performance. In addition, to improve sampling efficiency, we incorporate the self-play technique that allows the environment generator to automatically generate environments that are of great benefit to the training agent. Quantitatively, our approach, Diversity-induced Environment Design via Self-Play (DivSP), shows compelling performance over existing methods.
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学)
针对文本提示引导的生成模型,提出条件 Vendi 和条件 RKE 分数,通过条件熵分离模型自身多样性,并证明收敛性及在多个任务中恢复真实多样性排序。
Adaptive Test-Time Memory Allocation for Long-Tailed Human-Object Interaction Detection
College of Future Information Technology, Fudan University(复旦大学未来信息技术学院);School of Information Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学与技术学院);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI))
Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
Department of Computer Science, National University of Singapore, Singapore(新加坡国立大学计算机科学系);Smart Systems Institute, National University of Singapore, Singapore, Singapore(新加坡国立大学智能系统研究所)