Author

Evan Assmus

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling

This paper introduces a novel reward-model-free, critic-free, and gradient-based PbRL algorithm compatible with segment preferences named Segment Pairwise Proximal Policy Optimization (SP3O), and provides a theoretical basis for the algorithm and analyze the tradeoff in choosing the segment length.

Evan Assmus, Qining Zhang, Lei Ying · 0 citations