Research map / Reinforcement learning / Policy gradient and actor-critic
Error-Guided Bellman Calibration for Semi-Offline Value Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an error-guided extension of Bellman calibration for semi-offline value estimation, correcting a given value predictor's bias using a small on-policy sample alongside a large off-policy dataset.
Problem
Value estimation when a small on-policy sample supplements a large off-policy dataset, as in recommender systems and pre-deployment A/B testing; the goal is to use limited on-policy data to correct systematic bias in a given value predictor.
Approach
Builds on Bellman calibration (a post-hoc, model-agnostic correction along the predicted value) and makes the correction error-guided; the abstract is truncated, so the exact mechanism is not stated.
Experimental setup
Builds on: Bellman calibration
Closest papers by meaning
- Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation (NeurIPS 2024 · similarity 0.85)
- Contextual Online Pricing with (Biased) Offline Data (NeurIPS 2025 · similarity 0.84)
- Algorithms with Calibrated Machine Learning Predictions (ICML 2025 · similarity 0.84)
- Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL (ICML 2025 · similarity 0.84)
- Truthfulness of Calibration Measures (NeurIPS 2024 · similarity 0.84)
- Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.