Mitsuhiko Nakamoto

5 papers · 2023–2025 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)

Conferences

CORL (2) ICLR (1) NIPS (1) RSS (1)

Top co-authors

Sergey Levine (5) Aviral Kumar (4) Chelsea Finn (3) Anikait Singh (2) Abhishek Gupta (1) Simon Zhai (1) Seohong Park (1) Andrew Wagenmaker (1) Yanlai Yang (1) Oier Mees (1)

Research topics

Reinforcement Learning (1)

Keywords

conservative q-learning (2) offline reinforcement learning (2) few-shot learning (1) online fine-tuning (1) calibrated q-learning (1) robot manipulation (1) value function (1)

Papers

Steering Your Diffusion Policy with Latent Space Reinforcement Learning CORL 2025

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance CORL 2024

Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models ICLR 2024

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning NIPS 2023

Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials RSS 2023