A nested training ladder—train adaptive simulated partners at one level, then train the agent against them—improves coordination with unseen adaptive partners in Overcooked, but its non-collapse theorem restates its own assumption.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming
A nested training ladder—train adaptive simulated partners at one level, then train the agent against them—improves coordination with unseen adaptive partners in Overcooked, but its non-collapse theorem restates its own assumption.