Custom sampling for dqn

How severe does this issue affect your experience of using Ray?

  • Medium: It contributes to significant difficulty to complete my task, but I can work around it.

I am trying to train agent for Ludo, and want the training samples to have events of more strategic importance like killing the opponent, moving to safe spots etc. in training data. I am using a custom gymnasium environment. Any clue on how to strategically sample these points to send them to DQN?

Any help is greatly appreciated.

Hey @Kotha_Sri_Harsha ,

How about using a custom replay buffer that applies your intended logic at sampling time?