I'm training an RL agent/model (DRL/DQN).

Say that, for each learning step, the memory replay used by the agent to learn, has N elements (experiences) stored, where only X are unique elements (experiences), meaning X <= N.

I wonder whether it would be beneficial for the agent to sample from the whole memory or from a memory with unique elements?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.