arXiv:2602. 14344v2 Announce Type: replace-cross Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 15509v1 Announce Type: cross Abstract: Task guided agents demonstrate strong performance in a wide range of complex tasks.
arXiv:2602. 06746v2 Announce Type: replace Abstract: We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks.
arXiv:2602. 09761v2 Announce Type: replace-cross Abstract: In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments.
Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.
arXiv:2608. 13678v1 Announce Type: cross Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime.
arXiv:2604. 09686v2 Announce Type: replace Abstract: Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments.