Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis

no code implementations • CVPR 2022 • Tianhan Xu, Yasuhiro Fujita, Eiichi Matsumoto

Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh.

Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators

no code implementations • 16 Jul 2020 • Yasuhiro Fujita, Kota Uenishi, Avinash Ummadisingu, Prabhat Nagarajan, Shimpei Masuda, Mario Ynocente Castro

Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems.

reinforcement-learning Reinforcement Learning (RL) +1

ChainerRL: A Deep Reinforcement Learning Library

1 code implementation • 9 Dec 2019 • Yasuhiro Fujita, Prabhat Nagarajan, Toshiki Kataoka, Takahiro Ishikawa

In this paper, we introduce ChainerRL, an open-source deep reinforcement learning (DRL) library built using Python and the Chainer deep learning framework.

reinforcement-learning Reinforcement Learning (RL)

Learning Latent State Spaces for Planning through Reward Prediction

no code implementations • 9 Dec 2019 • Aaron Havens, Yi Ouyang, Prabhat Nagarajan, Yasuhiro Fujita

The latent representation is learned exclusively from multi-step reward prediction which we show to be the only necessary information for successful planning.

Model-based Reinforcement Learning reinforcement-learning +1

A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning

1 code implementation • 8 Feb 2019 • Yoshihiro Nagano, Shoichiro Yamaguchi, Yasuhiro Fujita, Masanori Koyama

Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure.

Representation Learning

Model-Based Reinforcement Learning via Meta-Policy Optimization

1 code implementation • 14 Sep 2018 • Ignasi Clavera, Jonas Rothfuss, John Schulman, Yasuhiro Fujita, Tamim Asfour, Pieter Abbeel

Finally, we demonstrate that our approach is able to match the asymptotic performance of model-free methods while requiring significantly less experience.

Model-based Reinforcement Learning reinforcement-learning +1

Clipped Action Policy Gradient

1 code implementation • ICML 2018 • Yasuhiro Fujita, Shin-ichi Maeda

We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation.

Continuous Control Policy Gradient Methods