Timeline for Choice of inputs features for Snake game
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 16, 2019 at 2:41 | comment | added | Anugraha Sinha | The ref given by you is a general suggestion for activation function for any type of NN. There is different between regression based problems and RL based problems. There are a couple of issues as to why you should not be using a softmax. It would be a little difficult to explain here, I will build markdown on github and share the link to explain this. | |
| May 15, 2019 at 21:10 | comment | added | johnhelt | I am wondering why you're suggesting to use a linear output function. I consider the problem to be a classification problem ("go straight", "go left", "go right"), and the NN to take the choice of the path with highest probability for maximizing the Q function. This post suggest the softmax function: stats.stackexchange.com/questions/218542/… | |
| May 14, 2019 at 12:59 | comment | added | johnhelt | You can find the code on my github repo. You can run the code from the main script (DDQN_algorithm_StackExhange.py)) | |
| May 14, 2019 at 8:28 | comment | added | Anugraha Sinha | Looking forward to the code link! | |
| May 14, 2019 at 8:18 | comment | added | johnhelt | Thanks for your reply. I have already added reward functions similar to what you're suggesting, and as I mentioned, I tried with an input state vector (10x10 = 100 elements), which is similar to what you say in point 2. I will try to run for longer time, but currently, after 300.000 steps, I did not improve one bit in the reward pr game, but the loss, calculated as the sum of the errors, does not change at all. I will try to upload my code to github and provide a link later if someone is interested. | |
| May 14, 2019 at 7:47 | history | edited | Anugraha Sinha | CC BY-SA 4.0 |
added 665 characters in body
|
| May 14, 2019 at 7:35 | review | First posts | |||
| May 15, 2019 at 15:58 | |||||
| May 14, 2019 at 7:35 | history | answered | Anugraha Sinha | CC BY-SA 4.0 |