In POMGs with decoupled dynamics and underlying Markov potential structure, independent learners converge to approximate Nash equilibria with quasi-polynomial complexity under filter stability.
Deep decentralized multi-task multi-agent reinforcement learning under partial observability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
In POMGs with decoupled dynamics and underlying Markov potential structure, independent learners converge to approximate Nash equilibria with quasi-polynomial complexity under filter stability.