ROP-RAS3 approximates long-horizon POMDP policies by sampling macro actions from state space via fast motion planners, scaling with sample count rather than action-space size and outperforming prior methods in success rate.
2402.09388 , archiveprefix =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Think Fast and Far: Long-Horizon Online POMDP Planning via Rapid State Sampling
ROP-RAS3 approximates long-horizon POMDP policies by sampling macro actions from state space via fast motion planners, scaling with sample count rather than action-space size and outperforming prior methods in success rate.