PTA: From Pretrained Representations to Acting Agents -- Bridging Pretraining, Planning, and Test-Time Decision Making

PTA examines how pre-trained representations become useful for acting and deciding. Researchers connect representation learning with reinforcement learning, planning, world models and control, asking what enables reliable, adaptable behaviour when a model is used in sequential decision settings. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.