arXiv Statistics ML
Prior-Data Fitted Networks for In-Context Off-Policy Evaluation
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Oct 7
Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models
arXiv:2610.07406v1 Announce Type: new Abstract: Active feature acquisition learns policies that sequentially acquire features to maximize information about a target variable. We study how to learn an...
arXiv AI
5d ago
A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation
The paper introduces PICLE-PFN, a foundation model for longitudinal causal effect estimation that handles dynamic treatment policies. It represents policies via in-context history-decision demonstrations and is pretrained on synthetic data from longitudinal structural causal models, enabling it to predict conditional average potential outcomes in a single forward pass without task-specific training. Experiments on synthetic and semi-synthetic benchmarks show competitive RMSE and better uncertainty calibration while reducing deployment runtime compared to conventional estimators.
arXiv Machine Learning
Oct 8
Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation
arXiv:2606.07399v3 Announce Type: replace-cross Abstract: Generative models are increasingly used to support decision-making in complex systems, where interventions may be joint and high-dimensional,...
arXiv Machine Learning
Oct 9
Amortized Off-Policy Evaluation for LLMs
The paper introduces PFN‑OPE, a prior‑data fitted network that performs amortized off‑policy evaluation (OPE) for large language models (LLMs). Unlike traditional OPE methods that must be retrained for each new logged dataset or reward definition, PFN‑OPE is pretrained once on a diverse set of contextual‑bandit tasks and can estimate value for any new logged dataset and target response in a single forward pass. Experiments on HelpSteer2 and UltraFeedback with Qwen, Llama, and Gemma policies show that PFN‑OPE reduces error by 2.0 to 9.3 times compared to the best baselines in reward‑shifted settings.
arXiv AI
Jul 14
Active Offline-to-Online Reinforcement Learning
arXiv:2607. 11720v1 Announce Type: cross Abstract: Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction.
arXiv Machine Learning
3d ago
Best Policy Tracking in Reinforcement Learning
The paper investigates how non‑monotonic performance dynamics in single‑task reinforcement learning affect policy selection. By introducing post‑hoc diagnostic metrics, the authors evaluate common selection strategies on continuous‑control benchmarks and find that typical practices often miss the best policy, leading to suboptimal performance and wasted computation. They propose a validation‑based selection method that better approximates the best visited policy while improving efficiency.