NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#soft-actor-critic

0 stories this week · 1 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedconstrained-mdp1 primal-dual1 reinforcement-learning1

2 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL26d ago

Parametric resonance can destabilize primal-dual learning in constrained MDPs

Mismatched constraint estimates drive resonance at twice the natural frequency; a shared estimate removes it but adds bias.

reinforcement-learning constrained-mdp

1

arXiv cs.AI / cs.LG / cs.CLSep 26, 2026

Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic

SAC study finds early |Q| growth predicts value-divergence flags, while rank collapse stays recoverable.

reinforcement-learning soft-actor-critic

2