Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments
Policy-gradient learning can deteriorate even after substantial initial improvement. We study this behavior in a repeated first-price auction setting with a sharp threshold between winning and losing bids. We identify a failure mode, zero collapse, in which a policy shifts into persistently near-zero reward as informative outcomes become rarely sampled. Experiments with REINFORCE and a TD state-value actor-critic illustrate this failure and evaluate practical mitigations. Adaptive update-magnitude control and smooth-output parameterization support sustained REINFORCE learning, while a learned baseline substantially stabilizes the fixed-rate comparison. Some actor-critic runs still collaps...
| Authors | Nishant Kumar, Enrique Areyan Viqueira, Amy Greenwald |
|---|---|
| Primary category | cs.LG |
| Published | 29 May 2026 |
| Last updated at source | 3 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.