学会発表・論文
-
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction
Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/2203.00494 -
arXiv:2203.11437
Self-Supervised Representation Learning as Multimodal Variational Inference
Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/2203.11437 -
IEEE International Conference on Robotics and Automation (ICRA) 2021
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/2007.14535 -
PLOS ONE
Panacea: Visual exploration system for analyzing trends in annual recruitment using time-varying graphs
Toshiyuki Yokoyama, Masashi Okada, Tadahiro Taniguchi
Link: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0247587 -
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020 ※採択率：47%
PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
Masashi Okada, Norio Kosaka, Tadahiro Taniguchi
Link: https://arxiv.org/abs/2003.00370 -
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020 ※採択率：47%
Domain-Adversarial and -Conditional State Space Model for Imitation Learning
Ryo Okumura, Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/2001.11628 -
IEEE International Conference on Robotics and Automation (ICRA 2020) ※採択率：42% (1,483/3,512)
Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor
Masashi Okada, Shinji Takenaka, Tadahiro Taniguchi
Link: https://arxiv.org/abs/1909.07031 -
Conference on Robot Learning (CoRL 2019) ※採択率：28% (110/398)
Variational Inference MPC for Bayesian Model-based Reinforcement Learning
Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/1907.04202 -
IEEE International Conference on Robotics and Automation (ICRA) 2018 ※採択率：40.6% (1,030/2539)
Acceleration of Gradient-based Path Integral Method for Efficient Optimal and Inverse Optimal Control
Masashi Okada, Tadahiro Taniguchi
Link: https://arxiv.org/abs/1710.06578 -
arXiv
Path Integral Networks: End-to-End Differentiable Optimal Control
Masashi Okada, Luca Rigazio, Takenobu Aoshima
Link: https://arxiv.org/abs/1706.09597
研究発表
-
第25回 画像の認識・理解シンポジウム (MIRU2022)
Self-Supervised Representation Learning as Multimodal Variational Inference
Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi
-
合同エージェントワークショップ&シンポジウム2015 (JAWS2015)
アトラクタ重畳に基づくマルチエージェント巡回
岡田雅司, 青島武伸