Multi-agent reach-avoid MDPs can be solved approximately using local feedback policies that are rank-one factorizations of global policies, formulated as a potential game with convergent iterative best response.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-agent Reach-avoid MDP via Potential Games and Low-rank Policy Structure
Multi-agent reach-avoid MDPs can be solved approximately using local feedback policies that are rank-one factorizations of global policies, formulated as a potential game with convergent iterative best response.