arXiv (All)
open access
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-zer
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning#1343251
- MENTOR: Learning from Failure with On-Policy Pedagogical Intervention#1297946
- MENTOR: Learning from Failure with On-Policy Pedagogical Intervention#1291852
- Controlling Collusion in Auctions: The Role of Ceilings and Reserve Prices#1274525
- Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards#1344343
Record · ID 1198934
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive