Reinforcement learning algorithm using two networks for stable Q-value learning.
Machine LearningReinforcement LearningAlgorithmArtificial Intelligence
Current best complexity is 10:
Double Q can be discovered in Concepts, categorized under Machine Learning, Reinforcement Learning, Algorithm, Artificial Intelligence. Reinforcement learning algorithm using two networks for stable Q-value learning.
It has been discovered by 6 boards and crafted 10 times, first appearing 4 months ago. Double Q can be created from 2 recipes, and goes on to appear as an ingredient in 6 others.
Double Q was first discovered by Hello5184's board 4 months ago. The lowest-complexity recipe (10) is held by Skitsboard.
Related concepts worth exploring include Vog, Infinite Loop, Gemini, Recursion, Robot, Artificial Intelligence, and 6 more.