A Hessian-free single-loop actor-critic algorithm achieves finite-time convergence to the unregularized bi-level RL optimum using attenuating entropy regularization under a special Polyak-Lojasiewicz condition.
dπ′ ρ = 1 2 dπ1 ρ + 1 2 dπ2 ρ .(93) We use ˆdπ ρ to denote the extend discounted visitation distribution over state and action such that ˆdπ ρ(s, a) =d π ρ(s)π(a|s)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
A Hessian-free single-loop actor-critic algorithm achieves finite-time convergence to the unregularized bi-level RL optimum using attenuating entropy regularization under a special Polyak-Lojasiewicz condition.