NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
65 results for “keyword:"policy evaluation"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Conditional Policy Advantage: Changing the Expert or Test Physics Can Reverse Policy Rankings▲11.00
[PDF]Provably Variance-Reduced Federated Categorical Distributional TD Learning with Linear Function Approximation▼5.8k2.33
[PDF]Reweight, Do Not Re-calibrate: Reusing the Same Encoder-Predictor Pair (World Model) When the Policy or Query Changes▼1351.33
[PDF]Does Imitation Learning Preserve Expert Performance Across Task Execution Speeds? A Benchmark Study▲3.0k2.33
[PDF]CompulsionBench: A Benchmark for Auditing Compulsion-Risk Proxies in Sequential Recommendation▼1.2k1.67
[PDF]Correlation Does Not Certify Reliable Evaluation: Identifiability Limits of World-Model-Based Robot Policy Selection▼4.3k2.00
[PDF]When Should LLM Agents Talk? Measuring Coordination Value and Auditing Learned Routers▼4.3k2.00
[PDF]Preserving Every Target Row Does Not Preserve Propagated Uncertainty in Recursive Fitted Evaluation▼4.5k2.67
[PDF]Beyond Decision Agreement: Evaluating Reinforcement Learning Policy Behavior and Outcomes in Power-System Balancing▼1.2k1.67
[PDF]What Success Rate Hides: Mapping Disturbance Tolerance in Vision-Language-Action Policies▼4.3k2.00
[PDF]GuardValue: Estimating One-Step Values and Policy Effects with Cloned Trajectory Prefixes▲3.0k2.33
[PDF]Selection Is Not Evaluation: Maximization Bias in Scoring Runtime Interventions for Language Agents▲11.00
[PDF]Every Failure Is a Timeout: Failure-Mode Homogeneity Makes Robot Policy Evaluators Unverifiable▼1.2k3.00
[PDF]Rehydration: Fixed-Semantics Counterfactual Replay for Mechanistic LLM-Agent Social Simulation▲5.4k3.00
[PDF]When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds▼1.2k1.67
[PDF]Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations▲14k2.50
[PDF]Generalizable World Simulator: Real-Time & Long-Horizon Interaction with Diverse Objects▼4.3k2.00
[PDF]ProWorld: Multi-View World Model with Proprioceptive Feedback for Closed-Loop Policy Evaluation▲5103.00
[PDF]From Anonymous Wallets to Behavioral Agents: A Calibrated Policy Test Bed for DAO Governance▼1.2k1.67
[PDF]FDR-Controlled Selection in Reinforcement Learning via Distributional Likelihood Ratios▲13k2.33
Withdrawn or desk rejected (11)
[PDF]SMART: Sequential Monitoring with Adaptive Risk Testing for Dynamic A/B ExperimentsWithdrawn1.33
[PDF]When Agents Change Their Own Test: Prospective Target Preservation under Candidate-Induced Task ExpansionWithdrawn1.33