A task-informed exploration policy learns which physical properties matter for a one-shot manipulation task, estimates them by poking, and switches to task execution when uncertainty is low.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Poke and Strike: Learning Task-Informed Exploration Policies
A task-informed exploration policy learns which physical properties matter for a one-shot manipulation task, estimates them by poking, and switches to task execution when uncertainty is low.