You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, I use reinforcement learning. During the meta training, I will test the model parameters trained every time in the training task, and get the following success rate. In the later stage, the success rate will be zero. Do you think this is correct?Why is it a little high in the early stage and zero in the later stage?
Give the result as follows:
-epoch is: 0, eval success rate is: 0.000
epoch is: 1, eval success rate is: 89.000
epoch is: 2, eval success rate is: 46.000
epoch is: 3, eval success rate is: 40.000
epoch is: 4, eval success rate is: 50.000
epoch is: 5, eval success rate is: 57.000
epoch is: 6, eval success rate is: 70.000
epoch is: 7, eval success rate is: 56.000
epoch is: 8, eval success rate is: 65.000
epoch is: 9, eval success rate is: 79.000
epoch is: 10, eval success rate is: 88.000
epoch is: 11, eval success rate is: 69.000
epoch is: 12, eval success rate is: 89.000
epoch is: 13, eval success rate is: 82.000
epoch is: 14, eval success rate is: 81.000
epoch is: 15, eval success rate is: 77.000
epoch is: 16, eval success rate is: 68.000
epoch is: 17, eval success rate is: 55.000
epoch is: 18, eval success rate is: 45.000
epoch is: 19, eval success rate is: 30.000
epoch is: 20, eval success rate is: 16.000
epoch is: 21, eval success rate is: 24.000
epoch is: 22, eval success rate is: 23.000
epoch is: 23, eval success rate is: 19.000
epoch is: 24, eval success rate is: 1.000
epoch is: 25, eval success rate is: 3.000
epoch is: 26, eval success rate is: 0.000
epoch is: 27, eval success rate is: 0.000
epoch is: 28, eval success rate is: 0.000
epoch is: 29, eval success rate is: 0.000
epoch is: 30, eval success rate is: 0.000
epoch is: 31, eval success rate is: 0.000
epoch is: 32, eval success rate is: 0.000
epoch is: 33, eval success rate is: 0.000
epoch is: 34, eval success rate is: 0.000
epoch is: 35, eval success rate is: 0.000
epoch is: 36, eval success rate is: 0.000
epoch is: 37, eval success rate is: 0.000
epoch is: 38, eval success rate is: 0.000
epoch is: 39, eval success rate is: 0.000
epoch is: 40, eval success rate is: 0.000
epoch is: 41, eval success rate is: 0.000
epoch is: 42, eval success rate is: 0.000
epoch is: 43, eval success rate is: 0.000
epoch is: 44, eval success rate is: 0.000
epoch is: 45, eval success rate is: 0.000
epoch is: 46, eval success rate is: 0.000
epoch is: 47, eval success rate is: 0.000
epoch is: 48, eval success rate is: 0.000
epoch is: 49, eval success rate is: 0.000
The text was updated successfully, but these errors were encountered:
Hello, I use reinforcement learning. During the meta training, I will test the model parameters trained every time in the training task, and get the following success rate. In the later stage, the success rate will be zero. Do you think this is correct?Why is it a little high in the early stage and zero in the later stage?
Give the result as follows:
-epoch is: 0, eval success rate is: 0.000
epoch is: 1, eval success rate is: 89.000
epoch is: 2, eval success rate is: 46.000
epoch is: 3, eval success rate is: 40.000
epoch is: 4, eval success rate is: 50.000
epoch is: 5, eval success rate is: 57.000
epoch is: 6, eval success rate is: 70.000
epoch is: 7, eval success rate is: 56.000
epoch is: 8, eval success rate is: 65.000
epoch is: 9, eval success rate is: 79.000
epoch is: 10, eval success rate is: 88.000
epoch is: 11, eval success rate is: 69.000
epoch is: 12, eval success rate is: 89.000
epoch is: 13, eval success rate is: 82.000
epoch is: 14, eval success rate is: 81.000
epoch is: 15, eval success rate is: 77.000
epoch is: 16, eval success rate is: 68.000
epoch is: 17, eval success rate is: 55.000
epoch is: 18, eval success rate is: 45.000
epoch is: 19, eval success rate is: 30.000
epoch is: 20, eval success rate is: 16.000
epoch is: 21, eval success rate is: 24.000
epoch is: 22, eval success rate is: 23.000
epoch is: 23, eval success rate is: 19.000
epoch is: 24, eval success rate is: 1.000
epoch is: 25, eval success rate is: 3.000
epoch is: 26, eval success rate is: 0.000
epoch is: 27, eval success rate is: 0.000
epoch is: 28, eval success rate is: 0.000
epoch is: 29, eval success rate is: 0.000
epoch is: 30, eval success rate is: 0.000
epoch is: 31, eval success rate is: 0.000
epoch is: 32, eval success rate is: 0.000
epoch is: 33, eval success rate is: 0.000
epoch is: 34, eval success rate is: 0.000
epoch is: 35, eval success rate is: 0.000
epoch is: 36, eval success rate is: 0.000
epoch is: 37, eval success rate is: 0.000
epoch is: 38, eval success rate is: 0.000
epoch is: 39, eval success rate is: 0.000
epoch is: 40, eval success rate is: 0.000
epoch is: 41, eval success rate is: 0.000
epoch is: 42, eval success rate is: 0.000
epoch is: 43, eval success rate is: 0.000
epoch is: 44, eval success rate is: 0.000
epoch is: 45, eval success rate is: 0.000
epoch is: 46, eval success rate is: 0.000
epoch is: 47, eval success rate is: 0.000
epoch is: 48, eval success rate is: 0.000
epoch is: 49, eval success rate is: 0.000
The text was updated successfully, but these errors were encountered: