Thank you for your help.
i managed to make the qlearning example work, it is a brilliant work created by you guys.
On another hand, the dqn-lidar example seems to have difficulty starting up the laser plugin:
[ INFO] [1495834673.773047535, 202.440000000]: Starting Laser Plugin (ns = /)!
Segmentation fault (core dumped)
Additionally, the dqn-camera example seems to have camera problem:
ValueError: Negative dimension size caused by subtracting 3 from 1 for 'Conv2D' (op: 'Conv2D') with input shapes: [?,1,32,32], [3,3,32,16].
Do you have any idea what might be happening?