ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
Sliding puzzles gym: A scalable benchmark for state representation in visual reinforcement learning
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
-
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.