Technology
Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
In Reinforcement Learning (RL), an agent engages with an environment in a sequential manner.
A Reduction-based Framework for Sequential Decision Making with Delayed Feedback Y unchang Y ang 1 Han Zhong 1 Tianhao Wu2 Bin Liu 3
More examples include but are not limited to robotics (Mahmood et al.,
Generalizable Implicit Motion Modeling for Video Frame Interpolation
Motion modeling is critical in flow-based Video Frame Interpolation (VFI).
Learning to Tokenize for Generative Retrieval Weiwei Sun 1, Lingyong Y an
Document retrieval plays an essential role in web search applications and various downstream knowledge-intensive tasks by identifying relevant documents to satisfy users' queries.
Supplementary Material A Data Modeling
In this section, we provide further details for our data modeling. We note the difficulties of appropriately modeling the terminal variable which is a binary variable compared to the rest of the dimensions which are continuous for the environments we investigate. This is particularly challenging for "expert" datasets where early termination is rare. An immediate advantage of sampling data from a generative model is compression. As we discuss in Appendix B.3, sampling is fast ER provides high levels of dataset compression without sacrificing downstream performance in offline reinforcement learning.
ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
Specifically, a set of prototypes is optimized to achieve per-task prototype overfit-ting, enabling accurately obtaining the overfitted prototypes for individual tasks. Furthermore, we introduce a task-guided diffusion process within the prototype space, enabling the meta-learning of a generative process that transitions from a vanilla prototype to an overfitted prototype.