Results 11 to 20 of about 57,740 (314)
Explainability in deep reinforcement learning [PDF]
Knowledge-Based Systems, 2021 Article accepted at Knowledge-Based ...
Heuillet, Alexandre +2 more
openaire +4 more sources
Abstraction for Deep Reinforcement Learning
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022 We characterise the problem of abstraction in the context of deep reinforcement learning. Various well established approaches to analogical reasoning and associative memory might be brought to bear on this issue, but they present difficulties because of the need for end-to-end differentiability.
Shanahan, M, Mitchell, M
openaire +3 more sources
Deep Reinforcement Learning with Adjustments [PDF]
2021 IEEE 19th International Conference on Industrial Informatics (INDIN), 2021 Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on real-world physical systems remains limited.
Hamed Khorasgani +3 more
openaire +3 more sources
An Introduction to Deep Reinforcement Learning [PDF]
Foundations and Trends® in Machine Learning, 2018 Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many
Peter Henderson +4 more
openaire +2 more sources
Deep Reinforcement Learning for Trading [PDF]
The Journal of Financial Data Science, 2020 16 pages, 3 ...
Zihao Zhang +2 more
openaire +3 more sources
Quantum compiling by deep reinforcement learning [PDF]
Communications Physics, 2021 AbstractThe general problem of quantum compiling is to approximate any unitary transformation that describes the quantum computation as a sequence of elements selected from a finite base of universal quantum gates. The Solovay-Kitaev theorem guarantees the existence of such an approximating sequence.
Moro, Lorenzo +3 more
openaire +5 more sources
Deep Reinforcement Learning with Double Q-Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2016 The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively.
Hado van Hasselt +2 more
openalex +4 more sources
Deep reinforcement learning of transition states [PDF]
Physical Chemistry Chemical Physics, 2021 RL‡can automatically locate the transition states of chemical reactions through deep reinforcement learning of feedback from molecular simulations.
Jun Zhang +7 more
openaire +5 more sources
The neurobiology of deep reinforcement learning [PDF]
Current Biology, 2020 In this primer, Ölveczky and Gershman review concepts and advances in deep reinforcement learning and discuss how these can inform the implementation of learning processes in biological neural networks.
Bence P. Ölveczky, Samuel J. Gershman
openaire +3 more sources
Learning Macromanagement in Starcraft by Deep Reinforcement Learning [PDF]
Sensors, 2021 StarCraft is a real-time strategy game that provides a complex environment for AI research. Macromanagement, i.e., selecting appropriate units to build depending on the current state, is one of the most important problems in this game. To reduce the requirements for expert knowledge and enhance the coordination of the systematic bot, we select ...
Wenzhen Huang +4 more
openaire +4 more sources