Takayuki Osa

Tokyo University of Science — Japan

Computer Science · Physical Sciences

20h-index1.9kcitations73works8.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(26), Robot Manipulation and Learning(20), Soft Robotics and Applications(20), Robotic Path Planning Algorithms(7), Surgical Simulation and Training(7)

Publications71 total

Autonomous parameter exploration in thermoplastic material-extrusion additive manufacturing using Bayesian optimization with intermediate features
Journal of Manufacturing Processes·2025Open Access
Uncertainty-aware Motion Planning based on Stochastic Forward/Inverse Kinematics Models for Tensegrity Manipulators
2025
Few-shot Imitation Learning by Variable-Length Trajectory Retrieval from a Large and Diverse Dataset
2025
Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps
arXiv (Cornell University)·2025Open Access
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Latent Space Curriculum Reinforcement Learning in High-Dimensional Contextual Spaces and Its Application to Robotic Piano Playing
2024· 1 cited
Active Learning for Forward/Inverse Kinematics of Redundantly-driven Flexible Tensegrity Manipulator
2024· 2 cited
Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
arXiv (Cornell University)·2024Open Access
Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks
2024· 2 cited
Touch-Based Manipulation with Multi-Fingered Robot using Off-policy RL and Temporal Contrastive Learning
2024
Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence·2024· 1 citedOpen Access
Forward/Inverse Kinematics Modeling for Tensegrity Manipulator Based on Goal-Conditioned Variational Autoencoder
2023· 3 cited
Learning Adaptive Policies for Autonomous Excavation Under Various Soil Conditions by Adversarial Domain Sampling
IEEE Robotics and Automation Letters·2023· 6 cited
Discovering diverse solutions in deep reinforcement learning by maximizing state–action-based mutual information
Neural Networks·2022· 20 cited
Sample-efficient parameter exploration of the powder film drying process using experiment-based Bayesian optimization
Scientific Reports·2022· 20 citedOpen Access
Motion planning by learning the solution manifold in trajectory optimization
The International Journal of Robotics Research·2022· 16 cited
Deep Reinforcement Learning With Adversarial Training for Automated Excavation Using Depth Images
IEEE Access·2022· 19 citedOpen Access
Parameter Optimization in the Drying Process of Catalyst Ink for PEFC Electrode Films with Few Cracks
ECS Meeting Abstracts·2021
Parameter Optimization in the Drying Process of Catalyst Ink for PEFC Electrode Films with Few Cracks
ECS Transactions·2021· 2 cited
page 1 of 4Next →

Frequent Co-authors

Naohiko Sugita(15), Mamoru Mitsuishi(15), Gerhard Neumann(7), Jan Peters(7), Masashi Sugiyama(7), Voot Tangkaratt(5), Alois Knoll(4), Keisuke Nagato(4), Tatsuya Harada(4), Yoshikazu Nakajima(4), Robert Bauernschmitt(3), Morio Tomizawa(3), Yuhei Yoshimitsu(3), Shuhei Ikemoto(3), Joni Pajarinen(2), J. Andrew Bagnell(2), Pieter Abbeel(2), C. Staub(2), Christoph Staub(2), Christian Farid Abawi(2)