Fixed Q Target is to protect targetQ changing because of the update of the neural network. TargetQ changing according to the update of the neural network could make the training process unstable.

University of Michigan - Ann Arbor

When updating the network for calculating the Q value, the network of selecting the best actions is not updated.

Fixed Q Target

Playing Atari with Deep Reinforcement Learning : https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
Human-level control through deep reinforcement learning : https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf

Learn Before

Related