arXiv (All)
open access
When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal
Does a reinforcement-learning agent that earns reward learn its task's hidden state? We study this question with hidden finite automata that the agent partially controls. Because each automaton is known, we can normalize reward by the best achievable return and probe the network for the true state a
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
- Pseudo-visibility: A Game Mechanic Involving Willful Ignorance#104906
- An Evaluation of a Punisher Assessment for Decreasing Automatically Reinforced Problem Behavior#448421
- Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning#1071099
- HSRM: Hidden-State Reward Models for Test-Time Verification#622586
- The Development of Reward Response to Food in Infancy#966440
Record · ID 986296
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