Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion that shows the right action has two explanations that the training data cannot tell apart: the model transferred the source clip, or it recovered a typical motion for th...
Zhi-Yuan Li, Wen-Yan Yang, Pekka Marttinen et al.· 0 citations
DAGR is proposed, which refines the static embedding of any late-fusion encoder into a state-conditioned one through multi-scale gated cross-attention, and traces the gain to the gated residual rather than to the difference bias that names the method.
This paper proposes SUccessor-to-Novelty (SUN), an indicator derived from successor value functions to identify goals that are both novel and reachable and presents an adaptive goal-selection strategy that leverages these properties, and an accurate yet lightweight pseudocount to avoid the overhead of classic methods.
Wen-Yan Yang, A. Mustafin, Dominik Baumann et al.· 0 citations
Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They still share one trait. None of them sees the current state. Such a state-independent embedding cannot mark which part of the goal still needs ac...
Xing Lei, Wenyan Yang, Xuetao Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
