ProRL learns interpretable programmatic scheduling policies via local search and Bayesian optimization on a custom DSL, matching or exceeding deep RL and heuristic baselines on benchmarks while using few training episodes.
Advances in Neural Information Processing Systems36, 74952–74965 (2023)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
An explainable LLM dialogue system for student behavior diagnosis outperforms baselines in evidence identification and increases trust among pre-service teachers in a small study.
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
citing papers explorer
-
Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework
ProRL learns interpretable programmatic scheduling policies via local search and Bayesian optimization on a custom DSL, matching or exceeding deep RL and heuristic baselines on benchmarks while using few training episodes.
-
Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
An explainable LLM dialogue system for student behavior diagnosis outperforms baselines in evidence identification and increases trust among pre-service teachers in a small study.
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.