A new class of closed-form decentralized policies is shown to be exponentially near-optimal in visibility for locally interdependent multi-agent MDPs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Thinking Beyond Visibility: A Near-Optimal Policy Framework for Locally Interdependent Multi-Agent MDPs
A new class of closed-form decentralized policies is shown to be exponentially near-optimal in visibility for locally interdependent multi-agent MDPs.