Is there any document illustrating how many training steps used to obtain the pre-trained model? Some pretrained model seems far less than the start-of-the-art. For instance, the dqn model on BeamRider and Qbert only achieve 948.0 and 550.0. However, using other policies (e.g., PPO2 and ACKTR), such reward values could be 10,000+.
It would be better if you can provide these pre-trained models as a trustworthy baseline for benchmarking.
araffin
commented
4 years ago
Is there any document illustrating how many training steps used to obtain the pre-trained model? Some pretrained model seems far less than the start-of-the-art. For instance, the dqn model on BeamRider and Qbert only achieve 948.0 and 550.0. However, using other policies (e.g., PPO2 and ACKTR), such reward values could be 10,000+. It would be better if you can provide these pre-trained models as a trustworthy baseline for benchmarking.