World Models Need Not Be Right to Rank Policies Right: Relative Bounds and Audit Limits
cs.LG, cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Imperfect World Models are Exploitable
- Offline Policy Comparison with Confidence: Benchmarks and Baselines
- WorldEval: World Model as Real-World Robot Policies Evaluator
- When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design
- Best-Arm Identification with Generative Proxy
- WorldGym: World Model as An Environment for Policy Evaluation
- Scalable Policy Evaluation with Video World Models
- Cross-Validation, Risk Estimation, and Model Selection
- How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis