UC Berkeley

Mitsuhiko Nakamoto

Advanced
@nakamotoo

I am a PhD student at Berkeley AI Research. My research interests focus on deep reinforcement learning for robotics.

nakamotoo.github.io

dsrl_pi0. Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

275

Cal-QL. official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)

122

V-GPS. official implementation for our paper Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance (CoRL 2024)

55

ecg-pytorch-sample. A PyTorch implementation for training deep learning models for 12-lead ECGs (2D-CNN, 1D-CNN, Transformer)

13

openpi. fork from https://github.com/Physical-Intelligence/openpi

3

dopamine. forked from https://github.com/google/dopamine

3

minibullet. Jupyter Notebook

1

pybullet_meshes. HTML

1
8
Apply