conftrace_

reward sampling

3 papers

Explore in graph

Co-occurring keywords

combinatorial object (2) sampling method (109) sampling policy (4) automated scoring (39) quadratic weighted kappa (12) accuracy estimation (13) human-computer collaboration (5) action-value estimate (2) human scoring (1) action-value estimation (1)

Papers

Efficient Contextual Bandit Learning via Reward-Space Sampling and Online Optimization (Student Abstract) AAAI 2026
QGFN: Controllable Greediness with Action Values NIPS 2024
Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees AAAI 2022