Seaquest-v0 not training as well as announced about rl_a3c_pytorch HOT 5 CLOSED

I have just watched the video created by gym-eval.py : what happens is that the agent kills all the enemies perfectly, but has never learned to surface !
Here's a gif:

Any idea why it stays at the bottom like that ?

from rl_a3c_pytorch.

Yup takes a long time for it to learn to surface correctly. Remember it took like nearly 24hrs then score started to shoot up. That game took nearly 3days if I remember correctly. Just let it keep training and it will sort itself out. As you can see it can shoot well so once the surfacing skill learned score should rise quickly after that

from rl_a3c_pytorch.

Got it, thanks ! Back to training then.
Do you think increasing the coefficient in front of the entropy term (currently 0.01) in the loss would make the agent discover the surface quicker by encouraging exploration ?

from rl_a3c_pytorch.

I think its good to leave the entropy term as is as its robust and effective for all games. I think massive exploration is one of the most important advantages of ai to humans so should not be neglected.

Added trained seaquest-v0 model to trained_models folder.

from rl_a3c_pytorch.

Ok for the entropy, and thanks for the trained model !

from rl_a3c_pytorch.