Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation.

Autor: Lu, Gaoxiong¹ (AUTHOR) gxlu22@m.fudan.edu.cn, Yan, Zeyu¹ (AUTHOR), Luo, Jianing¹ (AUTHOR), Li, Wei¹ (AUTHOR) fd_liwei@fudan.edu.cn

Publikováno v: Biomimetics (2313-7673). Nov2024, Vol. 9 Issue 11, p712. 17p.

Grandmaster level in StarCraft II using multi-agent reinforcement learning.

Autor: Vinyals O; DeepMind, London, UK. vinyals@google.com., Babuschkin I; DeepMind, London, UK., Czarnecki WM; DeepMind, London, UK., Mathieu M; DeepMind, London, UK., Dudzik A; DeepMind, London, UK., Chung J; DeepMind, London, UK., Choi DH; DeepMind, London, UK., Powell R; DeepMind, London, UK., Ewalds T; DeepMind, London, UK., Georgiev P; DeepMind, London, UK., Oh J; DeepMind, London, UK., Horgan D; DeepMind, London, UK., Kroiss M; DeepMind, London, UK., Danihelka I; DeepMind, London, UK., Huang A; DeepMind, London, UK., Sifre L; DeepMind, London, UK., Cai T; DeepMind, London, UK., Agapiou JP; DeepMind, London, UK., Jaderberg M; DeepMind, London, UK., Vezhnevets AS; DeepMind, London, UK., Leblond R; DeepMind, London, UK., Pohlen T; DeepMind, London, UK., Dalibard V; DeepMind, London, UK., Budden D; DeepMind, London, UK., Sulsky Y; DeepMind, London, UK., Molloy J; DeepMind, London, UK., Paine TL; DeepMind, London, UK., Gulcehre C; DeepMind, London, UK., Wang Z; DeepMind, London, UK., Pfaff T; DeepMind, London, UK., Wu Y; DeepMind, London, UK., Ring R; DeepMind, London, UK., Yogatama D; DeepMind, London, UK., Wünsch D; Team Liquid, Utrecht, Netherlands., McKinney K; DeepMind, London, UK., Smith O; DeepMind, London, UK., Schaul T; DeepMind, London, UK., Lillicrap T; DeepMind, London, UK., Kavukcuoglu K; DeepMind, London, UK., Hassabis D; DeepMind, London, UK., Apps C; DeepMind, London, UK., Silver D; DeepMind, London, UK. davidsilver@google.com.

Publikováno v: Nature [Nature] 2019 Nov; Vol. 575 (7782), pp. 350-354. Date of Electronic Publication: 2019 Oct 30.

A Generative Model to Embed Human Expressivity into Robot Motions.

Autor: Osorio, Pablo^1,2 (AUTHOR) ryusuke.sagawa@aist.go.jp, Sagawa, Ryusuke^1,2 (AUTHOR), Abe, Naoko³ (AUTHOR) naoko.abe1@naverlabs.com, Venture, Gentiane^2,4 (AUTHOR)

Publikováno v: Sensors (14248220). Jan2024, Vol. 24 Issue 2, p569. 19p.

Learning More May Not Be Better: Knowledge Transferability in Vision-and-Language Tasks.

Autor: Chen, Tianwei, Garcia, Noa, Otani, Mayu, Chu, Chenhui, Nakashima, Yuta, Nagahara, Hajime

Publikováno v: Journal of Imaging; Dec2024, Vol. 10 Issue 12, p300, 22p

Real-Time Policy Optimization for UAV Swarms Based on Evolution Strategies.

Autor: Chen, Zeyu, Liu, Haiying, Liu, Guohua

Publikováno v: Drones (2504-446X); Nov2024, Vol. 8 Issue 11, p619, 16p