Frequently Asked Questions

Installation problems

Tensorflow dependency

ML Agents requires TensorFlow; if you don't already have it installed, pip will try to install it when you install the ml-agents package.

If you see a message like this

ERROR: Could not find a version that satisfies the requirement tensorflow<2.0,>=1.7 (from mlagents) (from versions: none)
ERROR: No matching distribution found for tensorflow<2.0,>=1.7 (from mlagents)

it means that there is no version of TensorFlow for your python environment. Some known potential causes are:

You're using 32-bit python instead of 64-bit. See the answer here for how to tell which you have installed.
You have the tensorflow-gpu package installed. This is equivalent to tensorflow, however pip doesn't recognize this. The best way to resolve this is to update to tensorflow==1.15.0 which provides GPU support in the same package (see the release notes for more details.)
You're on another architecture (e.g. ARM) which requires vendor provided packages.

In all of these cases, the issue is a pip/python environment setup issue. Please search the tensorflow github issues for similar problems and solutions before creating a new issue.

Visual C++ Dependency (Windows Users)

When running mlagents-learn, if you see a stack trace with a message like this:

ImportError: DLL load failed: The specified module could not be found.

then either of the required DLLs, msvcp140.dll (old) or msvcp140_1.dll (new), are missing on your machine. The import tensorflow command will print this warning message.

To solve it, download and install (with a reboot) the install Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019.

For more details, please see the TensorFlow 2.1.0 release notes and the TensorFlow github issue.

Environment Permission Error

If you directly import your Unity environment without building it in the editor, you might need to give it additional permissions to execute it.

If you receive such a permission error on macOS, run:

chmod -R 755 *.app

or on Linux:

chmod -R 755 *.x86_64

On Windows, you can find instructions.

Environment Connection Timeout

If you are able to launch the environment from UnityEnvironment but then receive a timeout error like this:

UnityAgentsException: The Communicator was unable to connect. Please make sure the External process is ready to accept communication with Unity.

There may be a number of possible causes:

Cause: There may be no agent in the scene
Cause: On OSX, the firewall may be preventing communication with the environment. Solution: Add the built environment binary to the list of exceptions on the firewall by following instructions.
Cause: An error happened in the Unity Environment preventing communication. Solution: Look into the log files generated by the Unity Environment to figure what error happened.
Cause: You have assigned HTTP_PROXY and HTTPS_PROXY values in your environment variables. Solution: Remove these values and try again.
Cause: You are running in a headless environment (e.g. remotely connected to a server). Solution: Pass --no-graphics to mlagents-learn, or no_graphics=True to RemoteRegistryEntry.make() or the UnityEnvironment initializer. If you need graphics for visual observations, you will need to set up xvfb (or equivalent).

Communication port {} still in use

If you receive an exception "Couldn't launch new environment because communication port {} is still in use. ", you can change the worker number in the Python script when calling

UnityEnvironment(file_name=filename, worker_id=X)

Mean reward : nan

If you receive a message Mean reward : nan when attempting to train a model using PPO, this is due to the episodes of the Learning Environment not terminating. In order to address this, set Max Steps for the Agents within the Scene Inspector to a value greater than 0. Alternatively, it is possible to manually set done conditions for episodes from within scripts for custom episode-terminating events.

4.6 KiB 原始文件 文件历史