TCAB couples multiple adaptive policies on a tree, shares rewards when their complete context-action pairs match, and preserves each policy's standalone trajectory law at cost T plus cumulative edge disagreement.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
TCAB couples multiple adaptive policies on a tree, shares rewards when their complete context-action pairs match, and preserves each policy's standalone trajectory law at cost T plus cumulative edge disagreement.