arXiv (All)
open access
CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization
Learned visual reward models are increasingly used to optimize robot policies, yet a reward model can score an execution that acts on the wrong object as highly as one that completes the task. We show that optimizing such a reward can amplify these wrong-object failures while reward and task success
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
- VLA-$Δ$: Learning Physical State Transition for Vision-Language-Action Models#1356642
- Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning#1117857
- Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures#1296444
- ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies#267666
- Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies#1118726
Record · ID 1186841
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