COSAC enables scalable per-agent policy gradients in sequential cooperative teams via ridge regression on additive reward decomposition and counterfactual advantages from fictitious policy continuations, extending aristocrat utility with controlled bias-variance bounds.
Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, and Shimon Whiteson
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
COSAC enables scalable per-agent policy gradients in sequential cooperative teams via ridge regression on additive reward decomposition and counterfactual advantages from fictitious policy continuations, extending aristocrat utility with controlled bias-variance bounds.