Jim Huang

tensorflow 1.1 with CUDA 9.1

1

Where did you gedit the release file code , I want to use tensorflow 1.1 under the CUDA 9.1 ?

Question about /dataset/mujoco.py

2

What the different between [gail-tf/dataset/mujoco.py](https://github.com/andrewliao11/gail-tf/blob/ad92f41c26c34e8fabc536664fb11b44f25956cf/gailtf/dataset/mujoco.py#L36-L59) with [openai/baselines/baselines/gail/dataset/mujoco_dset.py](https://github.com/openai/baselines/blob/23b2333238e9850a230f0fa3ce95497d4c6c418b/baselines/gail/dataset/mujoco_dset.py#L42-L58)

It seems that without use normalised, the network still running and convergence.

sudo ./fullBuild.bash ``` [sudo] password for jim: optional install : astyle optional install : cppcheck optional install : cpplint optional install : valgrind optional install : xml INFO : 4...

If use Cuda-10.1 do not need to install `nvidia-cuda-dev` `nvidia-cuda-toolkit`, it will have error when you `apt-get install` any dependencies like this: ``` You might want to run 'apt-get -f...

Question about visualize the change of reward when training

1

Why we use `test()` to see the reward and testing_sample_step? Can I use the `train()` to see how the reward change when training? It seems that the `last perf` is...

I am seeking some products that can be used to positioning between human and mobile robot in wild. Do you have any solution?

`VelocityThirdOrderStep1` limitation

1

Input: ``` inp.control_interface = ControlInterface.Velocity inp.synchronization = Synchronization.No inp.current_position = [0] inp.current_velocity = [5] inp.current_acceleration = [-1] inp.target_position = [20] inp.target_velocity = [4] inp.target_acceleration = [-3] inp.max_velocity = [5] inp.max_acceleration...