UPD trains cooperative agents by adaptively selecting randomly generated partners with high return variance, outperforming population-based and population-free baselines in foraging, cooking, and with humans.
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
-
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
UPD trains cooperative agents by adaptively selecting randomly generated partners with high return variance, outperforming population-based and population-free baselines in foraging, cooking, and with humans.