Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Chenjun Xiao"'
Publikováno v:
Journal of Physics: Conference Series. 2390:012082
Robotic assembly is an important process to replace manual picking in industrial smart manufacturing. One of the important steps in assembly is robotics grasping and sorting of the workpiece. In this paper, a lightweight visual epigynous system was d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d705c277097c1b05b5b1f085d227a8ea
https://doi.org/10.1088/1742-6596/2390/1/012082
https://doi.org/10.1088/1742-6596/2390/1/012082
Publikováno v:
IEEE Transactions on Computational Intelligence and AI in Games. 9:88-102
Automatically acquiring domain knowledge from professional game records, a kind of pattern learning, is an attractive and challenging issue in computer Go. This paper proposes a supervised learning method, by introducing a new generalized Bradley-Ter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::164e46c794f5289f739c156be5e14cf4
https://doi.org/10.1109/tciaig.2015.2504108
https://doi.org/10.1109/tciaig.2015.2504108
Publikováno v:
IJCAI
In this paper, we investigate Exploratory Conservative Policy Optimization (ECPO), a policy optimization strategy that improves exploration behavior while assuring monotonic progress in a principled objective. ECPO conducts maximum entropy exploratio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8e5f4449f2415c56337bb46ed371824
https://doi.org/10.24963/ijcai.2019/434
https://doi.org/10.24963/ijcai.2019/434
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
This paper proposes and evaluates Memory-Augmented Monte Carlo Tree Search (M-MCTS), which provides a new approach to exploit generalization in online real-time search. The key idea of M-MCTS is to incorporate MCTS with a memory structure, where each
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::098650c2cf31672d595a84e46e032ab0
https://doi.org/10.1609/aaai.v32i1.11531
https://doi.org/10.1609/aaai.v32i1.11531
Autor:
Martin Müller, Chenjun Xiao
Publikováno v:
Communications in Computer and Information Science ISBN: 9783319579689
Recently, Factorization Bradley-Terry (FBT) model is introduced for fast move prediction in the game of Go. It has been shown that FBT outperforms the state-of-the-art fast move prediction system of Latent Factor Ranking (LFR). In this paper, we inve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79d2e934b7903e0daad8e03737c3decd
https://doi.org/10.1007/978-3-319-57969-6_3
https://doi.org/10.1007/978-3-319-57969-6_3
Autor:
Chenjun Xiao, Martin Müller
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 30
In this paper, we investigate the move prediction problem in the game of Go by proposing a new ranking model named Factorization Bradley Terry (FBT) model. This new model considers the move prediction problem as group competitions while also taking t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3a297a020b70605d762953106dbf64c
https://doi.org/10.1609/aaai.v30i1.10180
https://doi.org/10.1609/aaai.v30i1.10180
Publikováno v:
ICGA Journal. 35:182-185
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d1bb405cb372b421ec4c8001d442d6e
https://doi.org/10.3233/icg-2012-35307
https://doi.org/10.3233/icg-2012-35307
Publikováno v:
The 26th Chinese Control and Decision Conference (2014 CCDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8e9c50e381f6f1b18498efa373ab30f
https://doi.org/10.1109/ccdc.2014.6852869
https://doi.org/10.1109/ccdc.2014.6852869