A policy-gradient algorithm, BSPG, explicitly drives the safety-cost residual to zero from either side of the feasibility boundary and proves residual convergence and stationarity on the active constraint set for the exact-gradient update.
Provably efficient model-free algorithms for non-stationary CMDPs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Boundary-Seeking Policy Gradient for Safe Reinforcement Learning
A policy-gradient algorithm, BSPG, explicitly drives the safety-cost residual to zero from either side of the feasibility boundary and proves residual convergence and stationarity on the active constraint set for the exact-gradient update.