Asynchronous-Methods-for-Deep-Reinforcement-Learning icon indicating copy to clipboard operation
Asynchronous-Methods-for-Deep-Reinforcement-Learning copied to clipboard
verified publisher icon Zeta36

Different final epsilons from the paper

Open SnowWalkerJ opened this issue 8 years ago • 0 comments

The paper states that the final epsilons should be [0.1, 0.01, 0.5]. But I noticed in your code they are [0.01, 0.01, 0.05] (Strangely there are two 0.01s). Is this a mistake or intentional improvement?

I'm tunning the model myself, while I'm not sure which hyper parameters are important.

SnowWalkerJ avatar Oct 20 '17 05:10 SnowWalkerJ