Quantum reinforcement learning
This article has no lead section. (Learn how and when to remove this template message) |
Quantum reinforcement learning (QRL) contains three sub-elements: policy, reward function and model. But unlike traditional reinforcement learning, quantum reinforcement learning algorithms are much different.[1] There are some promising scientific results that point to the fact that active reinforcement learning agents may perform better in a quantum world scenario.[2] In order to gain the full potential of quantum-enhanced machines, instead of concentrating on machine learning data analysis capability, machines must learn from interaction, which is one of the main features of reinforcement learning.[3]
References[edit]
- ↑ Tarn, Tzyh-jong T. J. T. J. "Quantum Reinforcement Learning". IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).
- ↑ Lamata, Lucas (2017-05-09). "Basic protocols in quantum reinforcement learning with superconducting circuits". Scientific Reports. 7 (1): 1609. doi:10.1038/s41598-017-01711-6. ISSN 2045-2322.
- ↑ Briegel, Hans J.; Taylor, Jacob M.; Dunjko, Vedran (2018-11-21). "Advances in Quantum Reinforcement Learning". doi:10.1109/SMC.2017.8122616.
This article "Quantum reinforcement learning" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Quantum reinforcement learning. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.