A sharp threshold at zero reach-weighted contingent action capacity governs whether self-play RL collapses to a deterministic exploitation attractor under asymmetric perturbations.
International Conference on Learning Representations , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Adversarial action removal in self-play RL inflicts greater damage than random masking or learned perturbations, persists across algorithms and domains, transfers between agents, and resists recovery through extended training.
citing papers explorer
-
A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning
A sharp threshold at zero reach-weighted contingent action capacity governs whether self-play RL collapses to a deterministic exploitation attractor under asymmetric perturbations.
-
When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning
Adversarial action removal in self-play RL inflicts greater damage than random masking or learned perturbations, persists across algorithms and domains, transfers between agents, and resists recovery through extended training.