Takayuki Osa

Identifiers

• name variant Takayuki Osa 0.60 · backfill

Papers (5)

1. Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games cs.LG · 2026 · author #2
2. Open X-Embodiment: Robotic Learning Datasets and RT-X Models cs.RO · 2023 · author #236
3. Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization cs.LG · 2019 · author #1
4. An Algorithmic Perspective on Imitation Learning cs.RO · 2018 · author #1
5. Hierarchical Policy Search via Return-Weighted Density Estimation cs.LG · 2017 · author #1

Mentions

• 2602.10894 #2 · arxiv_oai · confidence 0.70 Takayuki Osa

Frequent Coauthors

• Jan Peters 2 shared papers
• Masashi Sugiyama 2 shared papers
• Pieter Abbeel 2 shared papers
• Tatsuya Harada 2 shared papers
• Abby O'Neill 1 shared papers
• Abdul Rehman 1 shared papers
• Abhinav Gupta 1 shared papers
• Abhiram Maddukuri 1 shared papers
• Abhishek Gupta 1 shared papers
• Abhishek Padalkar 1 shared papers
• Abraham Lee 1 shared papers
• Acorn Pooley 1 shared papers
• Agrim Gupta 1 shared papers
• Ajay Mandlekar 1 shared papers
• Ajinkya Jain 1 shared papers
• Albert Tung 1 shared papers
• Alexander Khazatsky 1 shared papers
• Alex Bewley 1 shared papers
• Alex Herzog 1 shared papers
• Alex Irpan 1 shared papers