Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Li, Zechu"'
Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian distribution, hence restricting learning to a single behavioral mode.
Externí odkaz:
http://arxiv.org/abs/2406.00681
Autor:
Torne, Marcel, Simeonov, Anthony, Li, Zechu, Chan, April, Chen, Tao, Gupta, Abhishek, Agrawal, Pulkit
Imitation learning methods need significant human supervision to learn policies robust to changes in object poses, physical disturbances, and visual distractors. Reinforcement learning, on the other hand, can explore the environment autonomously to l
Externí odkaz:
http://arxiv.org/abs/2403.03949
Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation
Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times on a commodity GPU. Most prior
Externí odkaz:
http://arxiv.org/abs/2307.12983
Autor:
Liu, Xiao-Yang, Li, Zechu, Yang, Zhuoran, Zheng, Jiahao, Wang, Zhaoran, Walid, Anwar, Guo, Jian, Jordan, Michael I.
Publikováno v:
Deep Reinforcement Learning Workshop, NeurIPS 2021
Deep reinforcement learning (DRL) has revolutionized learning and actuation in applications such as game playing and robotic control. The cost of data collection, i.e., generating transitions from agent-environment interactions, remains a major chall
Externí odkaz:
http://arxiv.org/abs/2112.05923
Publikováno v:
ACM International Conference on AI in Finance, 2021
Machine learning techniques are playing more and more important roles in finance market investment. However, finance quantitative modeling with conventional supervised learning approaches has a number of limitations. The development of deep reinforce
Externí odkaz:
http://arxiv.org/abs/2111.05188
Publikováno v:
Games (20734336); Jun2023, Vol. 14 Issue 3, p41, 12p
Publikováno v:
In Tensors for Data Processing 2022:293-340
Autor:
Batselier, Kim, Bi, Yingyue, Boulanger, Jérémie, Boyer, Rémy, Caiafa, Cesar F., Chanussot, Jocelyn, Chatzichristos, Christos, Chen, Cong, Cohen, Nadav, Cui, Xudong, de Almeida, André L.F., Erol, Aybüke, Fang, Yiming, Favier, Gérard, Hunyadi, Borbála, Jawanpuria, Pratik, Jiang, Tai-Xiang, Karakasis, Paris A., Karmouda, Ouafae, Kasai, Hiroyuki, Kofidis, Eleftherios, Kolomvakis, Christos, Levine, Yoav, Li, Zechu, Liavas, Athanasios P., Lin, Zhouchen, Liu, Xiao-Yang, Liu, Yipeng, Long, Zhen, Lourakis, George, Lu, Canyi, Lu, Liangfu, Lu, Yingcong, Lykoudis, George, Mishra, Bamdev, Ng, Michael K., Papagiannakos, Ioannis Marios, Ren, Bo, Sharir, Or, Shashua, Amnon, Siaminou, Ioanna, Tsalidis, Christos, Van Eyndhoven, Simon, Van Huffel, Sabine, Walid, Anwar, Wen, Fei, Wies, Noam, Wong, Ngai, Wu, Zebin, Xu, Yang, Yang, Liuqing, Ye, Fei, Yokota, Tatsuya, Zhang, Zhonghao, Zhao, Qibin, Zhao, Xi-Le, Zhou, Pan, Zhu, Ce, Zniyed, Yassine
Publikováno v:
In Tensors for Data Processing 2022:xiii-xvii