Skip to content
conftrace_

off-policy data

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

preference learning (2) policy optimization (2) hypothetical behavior (1) on-policy data (1) implicit reward margin (1) preference bootstrapping (1) alignment (1) mixing (1) monotonic improvement (1) safe exploration (1)

Papers

SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins ICLR 2025 SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning ICML 2025 Learning Human Objectives by Evaluating Hypothetical Behavior ICML 2020 Divergence-Augmented Policy Optimization NeurIPS 2019 When to Trust Your Model: Model-Based Policy Optimization NeurIPS 2019