TreePO replaces independent RL rollouts with segment-based tree search and a hierarchical advantage estimator, reducing GPU hours by 22-43% at comparable or better benchmark accuracy.
Remax: A simple, effective, and efficient reinforcement learning method for aligning large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
TreePO replaces independent RL rollouts with segment-based tree search and a hierarchical advantage estimator, reducing GPU hours by 22-43% at comparable or better benchmark accuracy.