GLAM improves world model prediction in model-based RL by feeding state differences into two parallel Mamba modules and training agents on imagined variation-aware trajectories.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GLAM: Global-Local Variation Awareness in Mamba-based World Model
GLAM improves world model prediction in model-based RL by feeding state differences into two parallel Mamba modules and training agents on imagined variation-aware trajectories.