DECAF learns fair and efficient centralized allocations by decomposing fairness changes into per-agent rewards, and its split and fair-only variants Pareto-dominate FEN and SOTO on five multi-agent resource allocation domains.
On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment
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
-
DECAF: Learning to be Fair in Multi-agent Resource Allocation
DECAF learns fair and efficient centralized allocations by decomposing fairness changes into per-agent rewards, and its split and fair-only variants Pareto-dominate FEN and SOTO on five multi-agent resource allocation domains.