action-policy
smolvlm2-500m-action-policy-demo-datarepro-off-policy-learning-in-large-action-spaces-optimization-matters-more-than-estimation
Reproduction: Off-Policy Learning in Large Action Spaces - Optimization Matters More Than Estimation
Paper Information
Title: Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
OpenReview ID: srIStBTJiu
Conference: ICML 2026
Task: Compare optimization landscapes of IPS vs PWLL for off-policy policy learning
Reproduction Summary
This reproduction evaluates the paper's core thesis: optimization landscape (not… See the full description on the dataset page: https://huggingface.co/datasets/sabaridsnfuji/repro-off-policy-learning-in-large-action-spaces-optimization-matters-more-than-estimation.us-science-policy-bills
US Science Policy Bills
A stance-annotated corpus of 8,191 public-health-related bills from the United States federal Congress and 41 state legislatures, collected and classified by SAFE Action (Science and Freedom for Everyone Action Fund), a 501(c)(4) social welfare organization building open-source democratic tools for science-based policy.
To our knowledge this is the first openly published, stance-annotated dataset of state-level public health legislation. Raw legislative… See the full description on the dataset page: https://huggingface.co/datasets/SAFE-Action/us-science-policy-bills.