Zobrazeno 1 - 10 of 16 pro vyhledávání: '"Nicolas Bougie"'
1
Akademický článek
Shared communication for coordinated large-scale reinforcement learning control
Autor: Nicolas Bougie, Takashi Onishi, Yoshimasa Tsuruoka
Publikováno v: SICE Journal of Control, Measurement, and System Integration, Vol 16, Iss 1, Pp 27-37 (2023)
Deep Reinforcement Learning (DRL) recently emerged as a possibility to control complex systems without the need to model them mathematically. In contrast to classical controllers, DRL alleviates the need for constant parameter tuning, tedious design
Externí odkaz: https://doaj.org/article/fee8b01bb4c04877ba3d19d3040f774e
Zobrazit plný text záznamu
3
Hierarchical learning from human preferences and curiosity
Autor: Ryutaro Ichise, Nicolas Bougie
Publikováno v: Applied Intelligence. 52:7459-7479
Recent success in scaling deep reinforcement algorithms (DRL) to complex problems has been driven by well-designed extrinsic rewards, which limits their applicability to many real-world tasks where rewards are naturally extremely sparse. One solution
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ee9bf87d886d44224c4803564526232c
https://doi.org/10.1007/s10489-021-02726-3
Zobrazit plný text záznamu
6
Fast and slow curiosity for high-level exploration in reinforcement learning
Autor: Ryutaro Ichise, Nicolas Bougie
Publikováno v: Applied Intelligence. 51:1086-1107
Deep reinforcement learning (DRL) algorithms rely on carefully designed environment rewards that are extrinsic to the agent. However, in many real-world scenarios rewards are sparse or delayed, motivating the need for discovering efficient exploratio
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::68f3c9f22578fd034affcfb1b799aeaa
https://doi.org/10.1007/s10489-020-01849-3
Zobrazit plný text záznamu
7
Goal-driven active learning
Autor: Nicolas Bougie, Ryutaro Ichise
Publikováno v: Autonomous Agents and Multi-Agent Systems. 35
Deep reinforcement learning methods have achieved significant successes in complex decision-making problems. In fact, they traditionally rely on well-designed extrinsic rewards, which limits their applicability to many real-world tasks where rewards
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::78a0cf8dea45ab41538698c882427505
https://doi.org/10.1007/s10458-021-09527-5
Zobrazit plný text záznamu
8
Skill-based curiosity for intrinsically motivated reinforcement learning
Autor: Nicolas Bougie, Ryutaro Ichise
Publikováno v: Machine Learning. 109:493-512
Reinforcement learning methods rely on rewards provided by the environment that are extrinsic to the agent. However, many real-world scenarios involve sparse or delayed rewards. In such cases, the agent can develop its own intrinsic reward function c
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0f111e1c2f407d2d1c7ace092e605f60
https://doi.org/10.1007/s10994-019-05845-8
Zobrazit plný text záznamu
9
Intrinsically Motivated Lifelong Exploration in Reinforcement Learning
Autor: Nicolas Bougie, Ryutaro Ichise
Publikováno v: Advances in Intelligent Systems and Computing ISBN: 9783030731120
Long-term horizon exploration remains a challenging problem in deep reinforcement learning, especially when an environment contains sparse or poorly-defined extrinsic rewards. To tackle this challenge, we propose a reinforcement learning agent to sol
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bb8c30c9a98c89515c5080b2367a500f
https://doi.org/10.1007/978-3-030-73113-7_10
Zobrazit plný text záznamu
10
Towards High-Level Intrinsic Exploration in Reinforcement Learning
Autor: Nicolas Bougie, Ryutaro Ichise
Publikováno v: IJCAI
Deep reinforcement learning (DRL) methods traditionally struggle with tasks where environment rewards are sparse or delayed, which entails that exploration remains one of the key challenges of DRL. Instead of solely relying on extrinsic rewards, many
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5bed4a3cb36f812551f5e80916217983
https://doi.org/10.24963/ijcai.2020/733
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje