TO
Takayuki Osa
cs.LGcs.AIcs.ROstat.MLAlgorithmscs.MAReinforcement learningReinforcement, PsychologyRepresentation learningRobot learning
On Valency
published · living versionsW_5nx3c79v·v1 · currentpublished
Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning
with Shota Nomura, Yasuhiro Kato, Kazuki Ota, Naoki Shitanda +1
1 version
Preprints & journals
18 papers in the corpus · 2008–2025Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps2507.10843v1 · Motoki Omura, Yusuke Mukuta, Kazuki Ota et al.2025 · 0 citationsarXiv
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning2506.05968v2 · Motoki Omura, Kazuki Ota, Takayuki Osa et al.2025 · 0 citationsarXiv
Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning2406.05993v1 · Takayuki Osa, Tatsuya Harada2024 · 0 citationsarXiv
Offline Reinforcement Learning from Datasets with Structured Non-Stationarity2405.14114v2 · Johannes Ackermann, Takayuki Osa, Masashi Sugiyama2024 · 0 citationsarXiv
Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning2403.07704v1 · Motoki Omura, Takayuki Osa, Yusuke Mukuta et al.2024 · 1 citationarXiv
Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks2403.00344v2 · Takayuki Osa, Tatsuya Harada2024 · 2 citationsarXiv
Open X-Embodiment: Robotic Learning Datasets and RT-X Models2310.08864v9 · Abby O'Neill, Abdul Rehman, Abhinav Gupta et al.2023 · 111 citationsarXiv
Discovering diverse solutions in deep reinforcement learning by maximizing state-action-based mutual information.35523085 · Osa, Takayuki, Tangkaratt, Voot, Sugiyama, Masashi2022 · 24 citationsNeural networks : the official journal of the International Neural Network Society. 2022;152:90-104
Sample-efficient parameter exploration of the powder film drying process using experiment-based Bayesian optimization.35136097 · Nagai, Kohei, Osa, Takayuki, Inoue, Gen et al.2022 · 20 citationsScientific reports. 2022;12(1):1615
Motion Planning by Learning the Solution Manifold in Trajectory Optimization2107.05842v1 · Takayuki Osa2021 · 17 citationsarXiv
Learning the Solution Manifold in Optimization and Its Application in Motion Planning2007.12397v1 · Takayuki Osa2020 · 1 citationarXiv
Meta-Model-Based Meta-Policy Optimization2006.02608v5 · Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt et al.2020 · 5 citationsarXiv
Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes1912.04063v2 · Takayuki Osa, Shuhei Ikemoto2019 · 8 citationsarXiv
Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics1910.01465v2 · Johannes Ackermann, Volker Gabler, Takayuki Osa et al.2019 · 93 citationsarXiv
Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization1901.01365v2 · Takayuki Osa, Voot Tangkaratt, Masashi Sugiyama2019 · 30 citationsarXiv
An Algorithmic Perspective on Imitation Learning1811.06711v1 · Takayuki Osa, Joni Pajarinen, Gerhard Neumann et al.2018 · 677 citationsarXiv
Hierarchical Policy Search via Return-Weighted Density Estimation1711.10173v2 · Takayuki Osa, Masashi Sugiyama2017 · 11 citationsarXiv
Analysis and estimation of cutting-temperature distribution during end milling in relation to orthopedic surgery.18556234 · Sugita, Naohiko, Osa, Takayuki, Mitsuishi, Mamoru2009 · 63 citationsMedical engineering & physics. 2009;31(1):101-7
Career total: 74 works. 18 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.