A risk-seeking variant of conservative policy iteration finds strong agent-state policies for Dec-POMDPs with monotonic improvement and polynomial-time convergence to local optima.
Next”: which controls how partial policies are expanded and also returns their heuristic values; and “Select
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Risk-seeking conservative policy iteration with agent-state based policies for Dec-POMDPs with guaranteed convergence
A risk-seeking variant of conservative policy iteration finds strong agent-state policies for Dec-POMDPs with monotonic improvement and polynomial-time convergence to local optima.