Marco Pleines

This is how I implemented ppo_iter. ``` def ppo_iter(mini_batch_size, states, actions, log_probs, returns, advantage): batch_size = states.size(0) ids = np.random.permutation(batch_size) ids = np.split(ids, batch_size // mini_batch_size) for i in range(len(ids)):...

Hi, which environment are you referring to? A specific one or all of them? To be honest, I have never run my environments in internal mode.

You can use the external inference mode. Inside the jupyter notebook, just set **load_model** to **True** and **train_model** to **False**. Then the agent is put to action on its learned...

The latest model is loaded. Please track down the python code if you want more insights. I'm not using the internal mode, because TensorflowSharp is highly experimental.

Are you using a camera observation as input? So far its not been working for this environment. Continuous inputs, such as direction to the target and the velocity of the...

If you didn't change anything after cloning the project, there is one camera resolution setup on the brain. If you set it to 0, just the continuous state is used...

As I updated the whole repository to ml-agents' version 0.3b, the jupyter notebooks are not included anymore. Maybe your issue is gone with the new version of ml-agents. Refer to...

This is the log of the spawned container ``` Executing the command: jupyterhub-singleuser --ip="0.0.0.0" --port=8888 [W 2018-01-09 12:40:02.986 SingleUserNotebookApp configurable:168] Config option `open_browser` not recognized by `SingleUserNotebookApp`. Did you mean...

Are there any news on this concern? I'd really appreciate it, because I've got a Deep Reinforcement Learning training pipeline that trains a bot on goalie and striker tasks in...

We just got our paper accepted at the Conference on Games on training goalkeeping and striking agents, which were trained in a Unity-based adaption of the true Rocket League game....