Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Hu, Hengyuan"'
Despite the considerable potential of reinforcement learning (RL), robotic control tasks predominantly rely on imitation learning (IL) due to its better sample efficiency. However, it is costly to collect comprehensive expert demonstrations that enab
Externí odkaz:
http://arxiv.org/abs/2311.02198
Consider a robot tasked with tidying a desk with a meticulously constructed Lego sports car. A human may recognize that it is not appropriate to disassemble the sports car and put it away as part of the "tidying." How can a robot reach that conclusio
Externí odkaz:
http://arxiv.org/abs/2306.08651
Autor:
Sokota, Samuel, Farina, Gabriele, Wu, David J., Hu, Hengyuan, Wang, Kevin A., Kolter, J. Zico, Brown, Noam
The process of revising (or constructing) a policy at execution time -- known as decision-time planning -- has been key to achieving superhuman performance in perfect-information games like chess and Go. A recent line of work has extended decision-ti
Externí odkaz:
http://arxiv.org/abs/2304.13138
Autor:
Hu, Hengyuan, Sadigh, Dorsa
One of the fundamental quests of AI is to produce agents that coordinate well with humans. This problem is challenging, especially in domains that lack high quality human behavioral data, because multi-agent reinforcement learning (RL) often converge
Externí odkaz:
http://arxiv.org/abs/2304.07297
We consider the problem of making AI agents that collaborate well with humans in partially observable fully cooperative environments given datasets of human behavior. Inspired by piKL, a human-data-regularized search method that improves upon a behav
Externí odkaz:
http://arxiv.org/abs/2210.05125
Publikováno v:
Advances in Neural Information Processing Systems 2021. Vol 34. 8215--8228
The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not c
Externí odkaz:
http://arxiv.org/abs/2207.07166
Autor:
Hu, Hengyuan, Sokota, Samuel, Wu, David, Bakhtin, Anton, Lupu, Andrei, Cui, Brandon, Foerster, Jakob N.
Fully cooperative, partially observable multi-agent problems are ubiquitous in the real world. In this paper, we focus on a specific subclass of coordination problems in which humans are able to discover self-explaining deviations (SEDs). SEDs are ac
Externí odkaz:
http://arxiv.org/abs/2207.12322
Autor:
Zhao, Yang, Wang, Fei, Yan, Yufeng, Fang, Shuangfeng, Cai, Baihang, Huang, Jin, Gong, Xinru, Hu, Jian, Liu, Li, Hu, Hengyuan, Zhang, Yudan, Cai, Ziqi, Yan, Qing, Wang, Yong, Qiao, Liang, Yan, Minglei
Publikováno v:
In Desalination 28 January 2025 594
Autor:
Jacob, Athul Paul, Wu, David J., Farina, Gabriele, Lerer, Adam, Hu, Hengyuan, Bakhtin, Anton, Andreas, Jacob, Brown, Noam
We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior. Imitation learning is effective at predicting human actions but may not match the strength of expert humans, wh
Externí odkaz:
http://arxiv.org/abs/2112.07544
Autor:
Hu, Hengyuan, Han, Meisheng, Liu, Jie, Zheng, Kunxiong, Mu, Yongbiao, Zou, Zhiyu, Yu, Fenghua, Li, Wenjia, Zhao, Tianshou
Publikováno v:
In Future Batteries December 2024 4