Author

Takayuki Osa

h-index 5 View on Semantic Scholar

We have 2 of 22 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

Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning

QDOS (Quality-Diversity Offline Skill learning), a unified pipeline for robust offline-to-online learning, incorporates an Advantage-Weighted Quality-Diversity pretraining objective, which weights the skill extraction and diversity objectives by the estimated advantage of each trajectory segment.

Tanachai Anakewat, Takayuki Osa, Tatsuya Harada · 0 citations

Preprint Jul 2026

Learning the Supports for Categorical Critic in Reinforcement Learning

This work investigates the Gaussian Histogram Loss (HL-Gauss), a recent approach that reframes value estimation as classification by encoding each scalar Bellman target as a Gaussian-smoothed categorical target, and derives an objective that forms an upper bound on the mean-squared Bellman error.

Jen-Yen Chang, Takayuki Osa, Tatsuya Harada · 0 citations