Hello, everyone. I’m new to the RL, so I used the official examples to test the RL codes. For the “CartPole-v1” problem, I learn the codes from this page DQN example, we can see it shows the output with small duration at the end.
But when I test it on the Colab or in my own computer, I found it show the wrong big duration at the end whether by cpu or gpu.
How to solve this problem, I’m so confused for the code example.
this is the colab and my computer’s output
