Terms in Reinforcement Learning Based on Bellman Equation

Q-learning

  • The method of learning based on Bellman equation

Q-function

  • The function used by Q-learning to calculate q-value

Q-value

  • The output of q-function

Q-table

  • The q-function in the form of a table
  • This table can take a huge and scary amount of RAM

Q-network (DQN)

  • The q-function in the form of a neuralnet
  • This function is less accurate but takes much much less RAM
  • Deep Q-Network is another term for q-network.

You'll only receive email when they publish something new.

More from 19411
All posts