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

arXiv:2609.32819 · cs.AI, cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• AUC — 48× in this paper · explained in 2 episodes
• Reinforcement Learning — 29× in this paper · explained in 4 episodes
• Actor — 19× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 17× in this paper · explained in 2 episodes
• Calibration — 11× in this paper · explained in 7 episodes
• In International Conference on Machine Learning — 9× in this paper
• In International Conference on Learning Representations — 7× in this paper
• Soft Actor-Critic — 7× in this paper
• Adam — 5× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Continual Learning — 2× in this paper · explained in 2 episodes
• Soft Actor-Critic (SAC) — 2× in this paper · explained in 2 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Phase Transitions — 1× in this paper · explained in 2 episodes

Sources

• Towards Characterizing Divergence in Deep Q-Learning
• Layer Normalization
• Plasticity Loss in Deep Reinforcement Learning: A Survey
• Maintaining Plasticity in Continual Learning via Regenerative Regularization
• Ultra-Early Prediction of Tipping Points: Integrating Dynamical Measures with Reservoir Computing
• Disentangling the Causes of Plasticity Loss in Neural Networks
• Deep Reinforcement Learning and the Deadly Triad
• MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection