Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yazr on Tuesday October 11, 2016 @03:09PM
(#12687583)
IMHO yes.
It is probably an easy local maxima with relatively fast convergence
Far harder are
a. "planning" - finding the optimal path through sequential turns
b. generalizing the learned experience to a new, unseen situation
Would love the get feedback from the author on this
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by sp332 on Tuesday October 11, 2016 @03:30PM
(#12687744)
No, the function rewards staying in the middle of the track.
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yanpanlau on Tuesday October 11, 2016 @06:03PM
(#12688887)
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.
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yazr on Thursday October 13, 2016 @11:14AM
(#12701259)
Can you please explain you are learning a SPECIFIC track or a random one ?
How would the existing agent fare on a brand new track ?
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yanpanlau on Sunday October 16, 2016 @02:49PM
(#12720245)
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.
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by bluetwo on Friday October 14, 2016 @03:21PM
(#12710440)
Any news on the test? I'm curious.
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yanpanlau on Tuesday October 25, 2016 @11:30AM
(#12788784)
Please find the result below. I modified the reward function such that staying in the middle of the track is no longer required.
Re:Using Keras and Deep Deterministic Policy Gradient to pla...
by yanpanlau on Sunday October 16, 2016 @02:52PM
(#12720262)
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?
Given enough training, would the car learn to find the apexes of turns?