yanpanlau
Joined 10 years ago
Karma
0
Submissions
7
Member since
Jul 14
Recent submissions
Comment · 9 years ago
Just use linux
Comment · 10 years ago
Please find the result below. I modified the reward function such that staying in the middle of the track is no longer required.
Comment · 10 years ago
Hi Bluetwo, I am currently travelling to the San Francisco right now. Can you send me a e-mail [email protected] so I can contact you and e-mail you the result directly when I back to Hong Kong?
Comment · 10 years ago
Hi~I used Aalborg track as my training dataset and I used Alpine1 track as my validation dataset. The Alpine1 track is 3 times longer than Aalborg. As you can see on the video, the agent can drive reasonably OK on the validation dataset.
Comment · 10 years ago
Staying in the middle of the track is not a necessary requirement in the reward function. The reason I include it is to speed up the learning time in the beginning. You can remove it once you learn a reasonable policy and see it the agent can find the optimal apex path. I will do a test tonight.
Just like in human world : You first learn how to drive before you learn how to drift the car.
Comment · 10 years ago
It is quite easy to change the input features as pixels and fit into convnet under Keras (That's why I love Keras so much). However, gym_torcs only support 64x64 pixels and it is hard to see by human eyes, IMHO.