GSS replaces tree-based MCTS with shared successor state layers and SNIS backups, proving polynomial horizon sample complexity under density overlap conditions.
Continuous upper confidence trees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
GSS replaces tree-based MCTS with shared successor state layers and SNIS backups, proving polynomial horizon sample complexity under density overlap conditions.