activity
20172024
most citedUnifying Value Iteration, Advantage Learning, and Dynamic Policy Programming

2 citations · 5 across the 6 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.RO2024

Unsupervised Neural Motion Retargeting for Humanoid Teleoperation

Satoshi Yagi, Mitsunori Tada, Eiji Uchibe +3

This study proposes an approach to human-to-humanoid teleoperation using GAN-based online motion retargeting, which obviates the need for the construction of pairwise datasets to i…

cs.LG2024

Reward-Punishment Reinforcement Learning with Maximum Entropy

Jiexin Wang, Eiji Uchibe

We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives.…