Open hiahiahu opened 7 years ago
hi, i run this code with the initial parameters: model='m1' with game breakout-v0. after about 8days' gpu training, when the program finished, i evaluated the model and got average-reward 22.0, which has a big difference with your screenshot(score=300+)。
And another experiment only with the switch(duel=True, double_q=True) on, the model's average-reward equals 5.4. Even worse than the original DQN.
Is there any trick i missed ? thanks for your replay!
i also want to konw it
I wrote a dqn myself, but I also got a bad score. I suspect it's the environmental problem of gym
you can use 'BreakoutNoFrameskip-v0' instead 'Breakout-v0' ,because the environment in 0.17 version gym is diffrent
hi, i run this code with the initial parameters: model='m1' with game breakout-v0. after about 8days' gpu training, when the program finished, i evaluated the model and got average-reward 22.0, which has a big difference with your screenshot(score=300+)。
And another experiment only with the switch(duel=True, double_q=True) on, the model's average-reward equals 5.4. Even worse than the original DQN.
Is there any trick i missed ? thanks for your replay!